Today on the Salesforce Admins Podcast, it’s time for a deep dive with Josh Birk, who talks to Raveesh Raina, Principal Solutions Engineer at Salesforce.

Join us as we chat about what Prompt Builder can do and how to write effective prompts.

You should subscribe for the full episode, but here are a few takeaways from our conversation with Raveesh Raina.

Intro to Prompt Builder

Raveesh is the perfect person to talk to about Prompt Builder and all the cool stuff you can do with it. As a Solutions Engineer, he works with customers to implement the latest and greatest Salesforce innovations and right now, that’s Prompt Builder.

Prompt Builder takes all the power of LLMs and combines it with your Salesforce data. You can use it to help you write personalized emails to customers, build out records with more information, and much, much more.

The four prompt template types and what they do

Right now, there are four prompt template types in Salesforce:

1. The sales email template drafts an email you need to send to your customer. Some examples include introducing them to a new product, or reminding them about an appointment.

2. With the field generation template, you can quickly and easily populate or complete a specific field on a record page with a summary or description created by an LLM.

3. The record summary template does exactly what it says it does: summarizes a record. This one is really easy to use via Einstein Copilot, and his clients love it for meeting prep.

4. Finally, there’s the flex prompt template. This can be used anywhere and everywhere on the platform to create a customized prompt template that incorporates records from multiple objects simultaneously. An example would be to create a personalized product recommendation for a customer based on an Einstein Next Best Action.

With all of these prompt templates, you can dynamically ground them with data from Salesforce or Data Cloud. That gives the LLM the power to pull data from records or, with flows, from pretty much any object—standard or custom—in your Salesforce org.

How admins can write effective prompts

So how do you write effective prompts that do what you want them to do? Raveesh has four tips to share with us:

1. Be explicit about your expectations and goals. What are you hoping to get out of the response? The AI needs a clearly defined goal in order to generate a good response.

2. Contextualize the information. State if you want to add related records to contextualize the response.

3. Specify your role. What is the persona for which this prompt template is built?

4. Add limitations and set boundaries. For example, “do not exceed 500 characters.” The AI needs to be told, and sometimes told again, what not to do. This is especially important to think about as you test and refine your prompt in order to get consistent results.

There’s a lot more great stuff from Raveesh about building better prompts and how Salesforce protects your data, so be sure to listen to the full episode. And don’t forget to subscribe to hear more from the Salesforce Admins Podcast.

Podcast swag

• Salesforce Admins on the Trailhead Store

Learn more

• Blog: The Ultimate Guide to Prompt Builder | Spring ’24

• Trailhead: Get Started with Prompts and Prompt Builder

• Video: Salesforce Admins Innovate with Prompt Builder

• Podcast: Get to Know Prompt Builder with Marissa Scalercio

Admin Trailblazers Group

• Admin Trailblazers Community Group

Social

• Connect with Raveesh

• Salesforce Admins: @SalesforceAdmns 

• Mike on Threads: https://www.threads.net/@mikegerholdt/

• Mike on Tiktok: https://www.tiktok.com/@salesforce.mike

• Mike on X: @MikeGerholdt

Full show transcript

Josh Birk:

Greetings everybody. Guest host, Josh Birk here, to take another deep dive into a topic. And this week, the topic is going to be Prompt Builder and Building on Prompts. I am joined by my good old colleague, Raveesh Raina, who is one of the people who wrote, for instance, our Ultimate Guide to Prompt Builder. Now, with no other hesitation, let's get over and talk to Raveesh.

All right, today on the show, we welcome Raveesh Raina to tell us about all things Prompt Builder. Raveesh, welcome to the show.

Raveesh Raina :

Thank you very much, Josh. It's an honor to be here and thank you for having me.

Josh Birk:

Excellent. Well, let's start off with a little bit about you. Tell me, what is your current role at Salesforce?

Raveesh Raina :

So I am a Principal Solutions Engineer. I work predominantly with our account executives and account directors to helping customers get inspired with our latest and greatest innovations that we are publishing and that we are releasing into the market. So I have a specific focus towards financial services. I'm based out of Toronto, Canada, so I work with all of our major enterprise banks with a lot of the different innovations and as far as financial services cloud is concerned, which is our flagship industries product. So helping them get inspired and sharing ideas on how we can help them better meet their goals.

Josh Birk:

And was computer something you always wanted to get into?

Raveesh Raina :

No, it's definitely an area that I personally have tried to get better at.

Josh Birk:

Okay.

Raveesh Raina :

And it's definitely an amazing opportunity and an amazing space to be.

Josh Birk:

What did you go to college for?

Raveesh Raina :

So funnily enough, even though I am based out of Canada, I actually went to the United States for my undergrad and I did mechanical engineering.

Josh Birk:

Ah.

Raveesh Raina :

So I graduated from New Jersey Institute of Technology, NJIT, with a mechanical engineering degree. But life had a different set of actions for me and somehow, I ended up aligned to the Salesforce ecosystem a long time ago.

Josh Birk:

Nice. Okay. Now, today we're going to talk about Prompt Builder. And when customers ask you about Prompt Builder, they're not familiar with it, what's the early elevator pitch you give them?

Raveesh Raina :

I essentially tell customers that Prompt Builder is an easy to use tool, which allows them to send a predefined set of instructions to an AI model, with the expectation of getting a response that has both value and meaning to them. And by value and meaning, I'm specifically referring to within the context of the data that they are providing via their CRM for Salesforce.

Josh Birk:

Okay. And walk us through the four templates we have right now that frame that data and that value add?

Raveesh Raina :

Yeah, absolutely. So right now, as of today, we have four prompt template types, sales email prompt templates, that's the first one. The second one is going to be field generation. The third one is what we call flex prompt templates. And the fourth one is record summary prompt templates.

Josh Birk:

Yeah. Now, I think the first two there are pretty straightforward. We're generating an email to send out to somebody, and if we're summarizing or we're generating a field, it means instead of a human putting in things manually, the GenAI is going to create it. Tell me a little bit more about the second two because I feel they're off to the corners and they're also very different from each other. Right? What's the purpose of a flex template and what's the purpose of the record summary template?

Raveesh Raina :

Yeah, so what I'll do is let me tackle record summary template first.

Josh Birk:

Okay.

Raveesh Raina :

Just as its name suggests, a record summary template is used by an admin to summarize a record or to get a succinct overview of a particular record. It is best served, best delivered in the UI via Copilot. So that is what we've seen greatest success in, in that record summary prompt templates can be surfaced up via Copilot, but it allows the admin to summarize a record based on whatever data model that they have already implemented.

Josh Birk:

Got it.

Raveesh Raina :

So that's a record summary template. Now, flex prompt templates, they are really powerful and versatile because what they allow an admin to do is to connect up to five objects together in a prompt template for the purposes of grounding. Those five objects could be standard objects or custom objects. They don't have to be related to each other in any way, shape or form, but through the power of the UI that the admin is surfacing, they can ground the flex prompt templates with each of those different objects with the expectation of getting a response from the LLM.

Josh Birk:

And for listeners at home, if you have somehow missed all of the wonderful Salesforce marketing about Einstein Copilot, it is a conversational AI for your platform and we will discuss that in another episode. Now, when it comes to these kind of templates, let's focus on the sales email, as I think it's the most straightforward. Some people listening might be like, "Well, I already know how to generate an email. Why do I need generative AI to do this?" What do you think the value add specifically that these are being pulled in through an AI model and having a generative response as opposed to a human created one? Where do you think the power lies there?

Raveesh Raina :

So the way I like to think of it where generative AI sales email templates provide value is the fact that it provides an easy mechanism for a user to craft an email in a conversational style that includes human and natural language text into it. If I were to use a standard email template as an example, that is static text, but replaced with either merge fields or even sometimes even with related records. But it removes that humanality sort of, from crafting an email. And the recipient may recognize that this is static text, but with generative AI, it adds more humanity towards that email template type. So that's where I feel is some of that value added.

Josh Birk:

And I think to some people, they might be scratching their eyebrows there because they're like, "But Raveesh, I'm using a computer to generate this email." But I think that's exactly spot on because we've all gotten that email that's like, "Hello, first name at company name. Congratulations on your date." And it's like you know instantly, this isn't from a human, but what these GenAI models are really good at is mimicking a human-like response, this human-like writing. And so it's like you get something that's acting like it's somebody to draft an email every single time you're sending this out to somebody.

Raveesh Raina :

Absolutely. Absolutely. It adds a little bit more personalization to a piece of communication that was missing with your static email templates in the past.

Josh Birk:

And also, I think it's hard to do it on a podcast, right? It's hard to show it on the podcast, the power of being able to ground this in Salesforce data. Tell me a little bit about... For each one of these templates we're talking about, what kind of data can we bring into the AI model to let it represent whatever it is that we're trying to generate?

Raveesh Raina :

Absolutely. So the real power of our generative AI tools with Salesforce, in my personal opinion, is the fact that we allow admins and customers the option to dynamically ground these prompt templates. What we mean by dynamically grounding is adding placeholders in these prompt templates that will be automatically replaced with either merge fields directly from a record or related lists that trace back to the origin of that record, or even through the power of flows. Once again, get a subset of related records associated to that original parent record as well.

So dynamically grounding can be done using merge fields, related lists, flows to get subset of records. And you can take it two steps further by grounding with Apex classes or even through the power of Data Cloud data model objects as well.

Josh Birk:

And what I think is also going back to the old way of doing things and doing things with this way, using flow, but also just because it's a conversational model, you can instruct the AI to do things based on the data. So it's not just, "Say something about this person's description." It could also be like, "Based on the fact that this person has no survey scores, change your response based on that." And what are some things that people who have flow skills can do to apply that extra layer of logic? Give me a good example of something that would change the course of the outcome based on a flow?

Raveesh Raina :

Yeah, absolutely. So I did mention that the power of flows is the fact that you can get subsets of records. So for example, if I want to surface up using a generative AI response, a summary of all open cases associated to a client or an account. If I were to use the standard related list component or resource picker, then it would give me a summary of all the cases associated to an account, whether it's open, closed, escalated, high priority, so on and so forth. But with flows, if I just want to surface up open cases only, that is what I can do through the power of dynamic grounding as well.

Josh Birk:

And what I love about it, if anybody's here, maybe for some reason, you haven't dipped your toe into the flow pool, the flows we're talking about can be very... I can do these flows, and I'm not Jen Lee. Flows are her job. She's the one who goes like, "Oh yeah, flow can do that crazy, impossible thing. Wait a minute, I'm going to show you how." Going on the other side of the spectrum, tell me a little bit about how data cloud can help complete this picture?

Raveesh Raina :

Yeah, absolutely. So as we all know, Data Cloud is an amazing tool that unlocks an organization's ability to tap into their enterprise data. So what that means is that for an organization that is using Salesforce, they may have a good portion of their data sitting in CRM, sitting in Salesforce, but a lot of it could also be sitting off platform in, for example, a lot of organizations, they have a separate dedicated app for their orders or their accounting, or even if they have a public website or mobile app, then some of that web traffic is logged in those third party systems.

Josh Birk:

Yep.

Raveesh Raina :

So through the power of Data Cloud, if they want to bring those insights and have a summarization or generative AI information associated to that data, customers are able to take all of that third party data that is sitting in those systems and have that surfaced up in Data Cloud. And the power of Prompt Builder allows for grounding with those Data Cloud objects or data model objects, I should say, and then surface up that information directly within the flow of work in Salesforce.

Josh Birk:

Yeah. Now, let's take a couple steps back because we've been talking a lot about data and grounding the data, taking the data from sources like Data Cloud, and I think that a lot of people have cautionary tales about AI. Describe the Einstein Trust Layer to me and how does it keep all of this stuff safe?

Raveesh Raina :

So one of the biggest messages that we have is the fact that we have zero retention policies with all of the public AI model providers that we have partnerships with. Whether those are, as an example OpenAI. So what that means is that I think we have to also take a step back and appreciate the fact that Salesforce's number one value is trust. And what we mean by that is the fact that we value our customers, we value that they are trusting us to securing their data. And we also take it one step further in ensuring that we are not sharing their data in any way, shape or form with any of these third party AI model providers.

So a big part of the Einstein Trust Layer is the fact that we are not sharing customer data directly or indirectly with AI model providers there. And also at the same time, those AI models are not learning from Salesforce's and customers' data as well.

Josh Birk:

And to be clear there, it's not like some generally handshake between us and Sam Altman. We filter that stuff out. OpenAI does not have the chance to train their models based on our data because they never see it.

Raveesh Raina :

Correct. Absolutely.

Josh Birk:

Okay. And then just to bring this to another level, because we think about things like in P-term, P2 and privacy and stuff like that, that's also stuff that's not being shared with entities that don't need to see it.

Raveesh Raina:

That is correct. Yeah, absolutely. We as a company have gone the extra mile to ensure that PII, personally identifiable information, or PHI, that is not shared, and it is actively masked and obfuscated before it is even sent to an AI model for processing as well.

Josh Birk:

Got it. Now, you've written a blog post, Ultimate Prompt Builder Guide, thank you for that, it's very extensive, and in it you include some very good tips on how to effectively write a prompt. Give me the high level like what are some really good tips to let me be more effective with that?

Raveesh Raina:

Absolutely. So a couple of pointers that I will suggest as admins and customers are looking to design prompts are that there are a few different areas that you should try to focus on. First is be explicit in your instructions in terms of the expectations and goals as far as what is it that you're hoping to get out of the response. So making sure that you are setting those expectations. Second is contextualizing information, meaning that state if you are adding in some related records to further contextualize the set of instructions. Third would be to specify your role. What is the persona for which the prompt template was built out for, whether it was a customer support manager or an account executive?

An important aspect of the prompt template that I would suggest is also ensuring that you add limitations and setting boundaries, so by being explicit with instructions such as, "Do not exceed past 500 characters," as an example. That is an explicit instruction and a guardrail, ensuring that the prompt template is not going to give a response longer than 500 characters. So those are some areas that I would suggest that folks go in on as far as designing prompt templates.

Josh Birk:

Yeah, one of the earliest things I realized in working with AI was, and this is in general, AI has this sort of default setting, shall we say, like a default tone, a default style. It thinks its response should be two paragraphs long, paragraphs should be three to four sentences. It's almost exactly what we'd learned back in high school for what a good writing style was kind of thing.

Raveesh Raina:

Right.

Josh Birk:

And it will default to that all the time unless you tell it not to. My favorite thing what you just said is explicit.

Raveesh Raina:

Correct.

Josh Birk:

I would actually add to that explicit and occasionally repetitive.

Raveesh Raina:

Yes. Yes, absolutely. It doesn't hurt being repetitive with your instructions because it's about ensuring that the AI model is going to meet your expectations of a response that has both value and trust.

Josh Birk:

Right. Because this is dynamically generated, which means even if you see the thing that you wanted to do once, run it three more times.

Raveesh Raina:

Correct. Exactly.

Josh Birk:

Because it might break one of your rules at one of those points. And then one of favorite anecdotes I give people is, if you saw the Dreamforce '23 keynote, we use Prompt Builder to do a sales email, and to have some fun, we added emojis to the sales email, which worked about three times out of five.

Raveesh Raina:

Yes.

Josh Birk:

Right? The team kept on coming out, they're like, "How do you fix this?" I'm like, "I have no idea. I'm going to go talk to the AI and figure it out." What it turned out was I had to beat the AI over the head and be like, "Not just use an emoji with this email, make heavy use of emojis all through this email." Be very, very explicit.

Raveesh Raina:

Absolutely, [inaudible 00:03:52].

Josh Birk:

Now, unlike myself, you have actually had the advantage of working directly with customers on some of these issues, and feel free to nerd out on fintech and banks in general, but what are some specific problems that you've seen from customers? Obviously, if you need to not name names, that's great, but what are some specific problems that you're seeing Prompt Builder help solve?

Raveesh Raina:

Yeah, absolutely. I think one of the reasons why I have been able to talk to a lot of customers is just because I've been also listening to a lot of customers as well. I think one of the most glaring areas where generative AI and Prompt Builder can provide most value is the use case for meeting prep. So I'm a rep, or I'm a customer support manager, and I need to prepare for an upcoming engagement with a client for a meeting. Using generative AI, I can quickly get a succinct overview on a particular client with all of the different data points that has both value and meaning to me, which I can use as part of my conversation in that meeting with that client as well. So meeting prep or account summarization is of immense value where we are seeing a lot of success with sharing this value with customers, and they are absolutely head over heels signing up for using Prompt Builder to address this need.

Josh Birk:

Got it. Well, to learn more, everybody, we're going to point to Raveesh wonderful blog post. We'll point you to a couple of Trailhead resources, some help documents. Raveesh, thank you so much. I do have one final question for you. What is your favorite hobby?

Raveesh Raina:

My favorite hobby at the moment right now is cycling. I use that as an opportunity to bond and to spend time with my kids. I have a seven-year-old and four-year-old, so any chance we get, especially with the weather that we're having this summer, we go outside, we go for cycling around the trails and around our neighborhood. So yeah, right now it's cycling for me.

Josh Birk:

Wonderful. Raveesh, thank you so much for the great conversation and information. That was a lot of fun.

Raveesh Raina:

Thank you very much, Josh.

Josh Birk:

I want to thank Raveesh for sitting down with us this week. And as always, I want to thank you for listening. Now, if you want to learn more about this show and stories about being a Salesforce admin in general, go down over to admin.salesforce.com. Thanks again, everybody, and we will talk to you next week.

Today on the Salesforce Admins Podcast, we sit down for an Admin Evangelist roundtable discussion with Josh Birk, Jennifer Lee, and yours truly.

Join us as we chat about how AI can help you be a better Salesforce Admin and what you can do to improve your prompts.

You should subscribe for the full episode, but here are a few takeaways from our conversation with Josh Birk and Jen Lee.

Practice your AI prompts

With everything going on with Einstein Copilot and Prompt Builder, I wanted to bring the Admin Evangelists together to find out how they’re thinking about AI and what you should do to get ready.

The number one thing that everyone agreed on is to start practicing your AI prompts. Josh recommends seeing if you can get your LLM of choice to tell you a dad joke. Then try and get it to tell you a better one. Just like how we had to learn how to write a good Google query, you’ll quickly find out that some prompts are more effective than others.

Jennifer shares the story of how her husband used ChatGPT to help with their itinerary on their trip to Italy. They still had to double-check that the restaurants it recommended were still open and that the timing of everything made sense, but it was a great starting point for planning their vacation.

How Salesforce Admins can get help from AI

Both Josh and Jennifer also use AI to help with work. Jennifer’s found ChatGPT to be really helpful for writing formulas. She used to spend hours on Google trying to find an example that matched the exact scenario she needed. These days, she can just write a prompt with her specific parameters and get back something useful in seconds. If Salesforce gives her an error, she can tell ChatGPT about it and it’ll try to fix the code.

Josh, meanwhile, has been using AI to help generate Apex code from scratch when he’s spinning up a demo org. As he’s quick to point out, it’s not necessarily helpful for the maintenance and debugging tasks that most developers do on a daily basis, but it’s perfect for his particular use case.

The human in the loop

One last thing we talked about that I want to highlight is the importance of the human in the loop.

We used the example of someone calling a power company to find out why their electricity bill is higher. If a human has realized that the weather has a major effect on usage rates and created a screen flow to call the right API, then an AI might be able to give the customer the right answer. But you need a human in the loop to do that second-order thinking.

We’ll have even more about how Salesforce Admins can use AI next week in Josh’s deep dive episode, so be sure to subscribe to hear more from the Salesforce Admins Podcast.

Podcast swag

• Salesforce Admins on the Trailhead Store

Learn more

• Trailhead: Get Started with Prompts and Prompt Builder

 

Admin Trailblazers Group

• Admin Trailblazers Community Group

Social

• Jennifer on X: @JenWLee

• Josh on X: @JoshBirk

• Salesforce Admins: @SalesforceAdmns 

• Mike on Threads: https://www.threads.net/@mikegerholdt/

• Mike on Tiktok: https://www.tiktok.com/@salesforce.mike

• Mike on X: @MikeGerholdt

Love our podcasts?

Subscribe today or review us on iTunes!

 

Full show transcript

Mike Gerholdt:
So in the world of AI and GPTs, and I think one's called Hugging Face, maybe it's Hugging Chat, I don't know. There is a lot to learn and people maybe you're afraid of it or you haven't tried something out. I don't know. We've heard a lot as evangelists on the admin relations team. And so this week I wanted to dive in with all of the rockstar evangelists that I have. Josh Birk, our Senior Admin Evangelist, and Jen, our Lead Admin Evangelist. Also, everything flow about let's dive into prompts and let's start learning about prompts and what should we be afraid of or what shouldn't we be afraid of, or what should we start doing? So that was a really long, highly caffeinated intro, but welcome to the show, Jennifer and Josh.

Joshua Birk:
Thanks for having us.

Jennifer:
Hey.

Mike Gerholdt:
So I won't name names, but I have been around in the community, and I have heard people like, "Cool, oh, you've done something with ChatGPT." And to be frank, if you follow me on Instagram, you'll realize that my feed, sometime in March, quickly took over crazy images generated by Dall-E. Because I find it fascinating that I can give it words to a 1970s music classic rock and say, "Make a picture." And it will produce something that would take me years to put together. And sometimes it's crazy, and I have to share that with the world because I think that's just so cool. But I guess I'm not afraid to try things out. So that's where I was with the world of AI. Where do you guys fall?

Joshua Birk:
Well, first of all, I want to go back to something you just said about what's dangerous about talking to something like let's just call it ChatGPT. Just use that as the generic one since it's the most famous and most popular. But I go back to-

Mike Gerholdt:
It's like the Kleenex of AI.

Joshua Birk:
Yeah, exactly.

Mike Gerholdt:
Everybody knows about it.

Joshua Birk:
Exactly. And I'm going to say this and I'm going to add a huge caveat to it. But when it comes to going to especially a free one, and just tinkering around with it, it's the same thing that one of the best pieces of advice I ever got before I started programming on a pretty basic on an Apple II. And my teacher at the time, I don't even remember what the class was called, it wasn't computer science or anything like that. But basically he was like, "Do whatever you want. You're not going to break the computer." There's nothing you're going to do that's going to... Nothing's going to blow up. Nothing's going to go in smoke. 
The dangers of using AI right now is not the conversation you're having with the AI, it's what you do with the result. So Mike, you're posting things to Facebook. What's the nefarious outcome to that? There's not, right? Now, if I use the generation of AI to submit my legal brief without checking it, you might run into some troubles. But what I always tell people is just jump in and just try talking to it, because until you do... I usually start with have it tell you a dad joke, have it tell you five dad jokes. 
My favorite, actually, one of my favorites is go in and play 20 questions with it. Because having an AI guess the object that you're thinking in your brain is actually, it's an interesting way to prove how a conversational model works. But basically to go back to my teacher's advice, don't be scared. Go in an experiment.

Jennifer:
Yeah, I have to say that when it first came out, I wasn't one of the people who went running to play with it. But when we were planning our trip to Italy last year, my now husband went and used it to come up with the itinerary. He said, "Okay, we're going to start here. Here are the sites we're going to, recommend some restaurants for me." So then it came back and it said, "Okay, you should go here and here." He, of course, human in the loop, had to go verify that these restaurants still existed.

Mike Gerholdt:
Yup.

Joshua Birk:
Sure.

Jennifer:
But it helped put together our agenda. And then nowadays I've been using it to help me with formula creation, because I am the worst when it comes to the parens, commas, nested if statements, they drive me nuts. I used to spend hours Googling to find the exact scenario I needed that someone else posted, and then tweaked it. But now I can go and say, "ChatGPT, I need a if statement for three things. Give me the structure," and then I would put it in there. So it's been really helpful to me in that regard.

Joshua Birk:
And not to throw down Jen, but being the worst, I might have to, I'm not sure. I think I might be worse than you are, because I've done the same thing. And the nice thing is, so ChatGPT is what's called a chained conversational AI. Which means when you create that formula, if you get... Like you put it in and you get an error from Salesforce, you can give that error back to ChatGPT and be like, "You got this wrong," and it already has the context of the formula it gave you, and it'd be like, "Oh, you're right. Let me fix that for you."

Jennifer:
Right. 

Mike Gerholdt:
Yeah. And then just to clarify, in the context of what we're talking about, a prompt, because we spelled this out in our workshops, but a prompt is a starting line for an AI conversation or task where you tell the large language model what you're looking for using natural language, right?

Joshua Birk:
Yeah.

Mike Gerholdt:
So tell me this, because sometimes I struggle with this. How do you write your prompts differently, than say, putting in a search for Google?

Joshua Birk:
Yeah. So first of all, I think that's one of the reasons we call it... People are like, why prompt? It's a weird word. And I think the reason why we refer to it as prompt, because it's a more generic thing than saying query or question or request, or anything like that. Because the thing that you need to provide in a prompt... So let's compare those two directly. When you do a search in Google, it's basically going to a database of a whole bunch of really fancy stuff Google's done, and then you're always going to get the same answer. 
If you do the same prompt in ChatGPT you might get slightly different answers because that answer is being generated on the fly. And so in order to be successful with... The nice thing with ChatGPT, once again, because it's a chain conversation AI, so you can start slow and then just keep adding context to it. But in a non-chained one like Prompt Builder, it's adding in all the instruction and the explicit instruction, and the repeated instruction, and the context of, "No, that's sort of the response I wanted, but that's not exactly. Here's how to correct it," kind of thing. 
So to compare it to a Google search, it would kind of be like, no, give me the Google searches that are actually relevant to the problem I have at hand. Which Google can't do because it doesn't understand context.

Mike Gerholdt:
Right. That makes sense. Jen, you said human in the loop, and I feel like we've naturally in just comparing Google searches to prompting a GPT to return a result, naturally put the human in the loop. But what did your husband do in terms of planning to put the human in the loop for other things?

Jennifer:
Yeah, I mean, he had to go, even though it would return an itinerary for us of sites to see in Italy, he still had to go and check and say, "Okay, is this the right path that it should take?" Confirm the hours that... Even though it suggested here's the order, well, is it even open at that time, right? Can you imagine just showing up there and like, oh, nope, it's not open until noon, but you have me going there the first thing in the morning.

Mike Gerholdt:
Yeah. Or it figures your itinerary is you just drive there, spend one second there, back out of the driveway. 

Joshua Birk:
Right.

Mike Gerholdt:
Like, no, I'm going there for a reason.

Joshua Birk:
Yeah, it doesn't always get the context of time correctly the first time. The last time I tried to do an itinerary, it gave me so many things to do in three hours that no human being could possibly do it.

Mike Gerholdt:
Oh my goodness. Yeah. I will say I have tried... So one of the first things I experimented with was, I think it's called Gemini Now, because it was Google and it plugged into their Google Maps. And I think planning road trips and stuff, when you're looking for specific stops, not touristy stops, but okay, a couple hours into the drive, I'm going to want to stop and get some diesel. I want to take a break from driving for 10 or 15 minutes. 
I don't want to just sit there and figure out on the map and scroll mile by mile on the map. Does that look like a gas station? Does that look like a gas station? And have it go through that. But oftentimes I also have to go back through the map and validate like, oh, is that still open?

Joshua Birk:
Right. Yeah. So I think they've gotten better because these large models at one point were impossible to pre-train on small amounts of data. They basically had to re-consume the entire internet over and over again. And that's why when they first became popular, they warned you it doesn't understand anything. Basically pre-pandemic, if I remember right. And that was a problem here in Chicago because a lot of very famous places had shut down. 
So to your point, Jen, about itinerary, making sure they're still there, it would've been spot on recommendations in 2019, but now not so much. And again, I think they've learned how to train them with smaller bits of data. So I think this is better. But yeah, it's whatever moment in time it's looking at when it was grounded in that data.

Jennifer:
Well, when I was looking at free GPT products, I used Perplexity AI, and that was using the internet and not data up until a certain timeframe. 

Joshua Birk:
Nice.

Jennifer:
And it came back and said, here's my answer, but then here's my sources. 

Joshua Birk:
Nice.

Jennifer:
So then if I wanted, I could go click on that to get more information

Mike Gerholdt:
Yeah, as an article from 2007. Like, "Oh, cool, five star Michelin restaurant." What do you feel, in terms of using AI just for your everyday life, is helping you understand AI better as we work to understand the capabilities of prompt builder and copilot?

Joshua Birk:
So for work, I'm going to confess, because I've been using AI to generate a lot of APEX. And it's not that I can't write that APEX. And I'm going to say this because I think this is a very unique situation because I'm writing a lot of APEX that's from scratch. I'm not an enterprise developer who has to go in and maintain large bits of code and large project related code and things like that. And there's this huge question out there for the everyday developer, is AI something that's really useful? Because a lot of everyday development is maintenance and it's bug fixes and it's very detailed work.
And there's probably a role for AI when it comes to code reviews and things like that. But for what I'm using it for, it's like I know how to write this and I know I've written something like this, but AI will do it 90% correctly in about three seconds. I can't type that fast, especially these days. I cannot type that fast. And so if I just kind of go back in and I'll reiterate it and stuff like that, and because of that in very short period of time, for instance, the demo works we're spinning up. I have APEX that can recreate all the data for me in these styles.
And that's, I think, the important thing is it's in the style that I want the data to look like. It's in the level of realism that I want the data to look like. Which actually would've been... That's the part that would've been very difficult me to do because to sit back and be like, I want 30 companies that sound like they would work with Northern Trail Outfitters.

Mike Gerholdt:
Oh yeah.

Joshua Birk:
Right? I'd have to sit back and actually ideate about that and spit out ideas and all of this kind of stuff. And ChatGPT is just like-

Mike Gerholdt:
I'd come up with a whole bunch of Southern Trail Outfitters and Western Trail Outfitters and Eastern Trail Outfitters.

Joshua Birk:
Exactly, exactly. It's not shy. It will just try to give you that kind of slightly creative information shoved inside of an APEX class. And it's definitely, I mean, I can't even calculate how much time it saved me.

Jennifer:
I think for me, outside of the formula piece, which it has definitely helped me build formulas faster, but I use it to shorten things that I've written. Here's this thing, I need to narrow it down into this many characters. So that's been helpful in shortening that up. I have a problem of condensing things.

Mike Gerholdt:
No, I think that's great. I mean, that's actually to look back at admin track at Dreamforce a few years ago, the biggest session that was always attended was documenting your org. And I think it's because you always would have to start from scratch as opposed to, Jen, I use AI for a lot of that as well. I will write a description in X number of characters following this style of writing and then give me three versions of it. Because Josh, to your point, I don't have three versions in my head, or I need a fourth version, but I need you to give me three to kind of push the cart down the hill a little bit.

Joshua Birk:
Yeah. And it's like, why do we keep going back to summarization as such a classic AI use case? Part of it is because it can read it and then write that summarization faster than you could read it by a 100th percent. It can do it. So it's not just the speed of generation, it's the speed of consumption as well.

Mike Gerholdt:
So working with, looking ahead, because Prompt Builders GA, we're doing workshops. What are some of the things that we should think about as admins for what organizations may be looking for in terms of prompts, so that... Because I literally think the amount of creativity that we have in our heads is the limitations we all have for delivering on super useful prompts.

Joshua Birk:
Well, Mike, I don't know if you know this yet, but we have an upcoming episode with my friend Ravish [inaudible 00:14:47], where we talk about this a little-

Mike Gerholdt:
Next week. 

Joshua Birk:
Right. So one of the things I asked him, because Ravish actually is working with customers and working with billing out some of these solutions. And I think the answer to that question is start looking at... Let's focus very specifically on this field generation prompt builder template. Look at your page layout and ask yourself, is there something here, or can I add a field to this that would be useful? Because going back to our friend summarization, that we could summarize not just the object that we're looking at on the record, but summarize it in its related data. And it's a data next to it and data that Flow can find to it and data that's in Data Cloud and all of these points of data.
And what Ravish said, not to spoil my own content, but he's like, "One of the most useful things is either meeting prep or call prep." Like if you have a call with a customer coming up, you want to pull up the account and you want to get a one paragraph overview of all the activity of that account so that you are enlightened almost right away as to what to do with this. So I think it's going to be hard until you see the fields actually being generated, because it's a very different kind of data that we're used to. 
But the question is going to be, I'm trying to think of if, and maybe one of you two have a good example, because Salesforce has evolved so much over the years, right? I always joke with people, you don't know how good you have it because you can do GO selection and SOQL queries. I had to write an entire APEX class in order to make that work, and I couldn't even do it with Radius. I had to select zip codes by a square because we didn't have the capacity to do sign and co-sign back then. The things that we've added that make the platform so much more intelligent, and this is another step in that evolution. And so it's time to start asking yourself, what layer of generative data can I add to my object model that's going to make my users more successful?

Mike Gerholdt:
Yeah, I would agree. I think along those lines, looking at what's available, looking at what GPT, even if you can't get your hands on anything Einstein and all you do is Trailhead modules and you listen to some podcasts like this. I think the one thing, not that worries me, but the one thing that I would have a serious conversation sit down with stakeholders is I would look at what's all the anecdotal data that we store in Salesforce and where is it at? 
And so I bring that up because Josh, your example of zip codes, phone numbers, hard data, super hard data, a zip code, a phone number, even a street address anymore, you can write a call out and verify that. The number of websites I go to now, and I literally type the three numbers of my house in, and it's already narrowed it down to the five possible addresses this could be, I think is amazing, it didn't exist before. But what I think the power of what people are wanting is, so give me a summarization of the last five calls and what their pain points were.
And if you're not running some sort of reports or like Jen, if you don't have, I'm thinking screen flows with really good fields to prompt people on, you need to fill this stuff out and we need to prepare for it. I don't care how good the AI is, it's not going to weed through bad call notes if the salespeople didn't put that stuff in.

Joshua Birk:
Yeah. And I want to call out one of the demos I saw here internally, because I think it touches on that a lot. And the demo was case support, and I think this was Copilot. And the ticket was, "Why is my power bill so high?" And the AI doesn't know how to answer that question properly. And this is like when we keep the human in the loop, the human in the middle, we have to remember that's in the whole... It's from beginning to end, because a human had to realize, oh, we charge people for electricity. 
And what is one of the things that determines how much electricity you use? Oh, it's the weather. So what I'm going to do is I'm going to build a Flow that calls out to the weather API that brings me back the weather for the last whatever period of time this ticket was for. And then the AI is like, oh, well, your power bill was high because it was super cold, or it was super hot, or whatever. But the case support person can basically just ask, analyze the support ticket and with the power of Flow that a human created, then the AI can add into it and be like, oh, this is why we think this is wrong.

Jennifer:
Yeah. I think back to the demo that we created for Dreamforce, for the admin keynote, we were using NTO, right? They did expeditions and we were able to say, okay, take the customer's expeditions that they've already been on and take the customer state, and then now go and based on what they've done in the past, recommend something similar. And looking at all the expeditions that were available. So that would've taken some time for the rep to then go research that and see what expeditions they've been to, what they might like, based on those things, to recommend other things. But with Prompt Builder and field generation, click a button, AI does it all for you.

Mike Gerholdt:
I would agree. Well, thanks for sitting around and jawing about prompts and GPTs, because I feel like it's June, we've been talking about this... Has it been for over a year or has it just been a few months? Or has it just been a year-

Joshua Birk:
It feels like over a year.

Mike Gerholdt:
Right. Right. But it's a little more advanced. It's interesting because I wonder in a year from now if we listen to this episode, if it'll sound super dated or not.

Joshua Birk:
Yeah, I think that's an interesting question. And it's hard to answer because you have OpenAI saying the AI you're talking to right now are, oh gosh, I think I'm trying to remember their exact quote and realizing it might not be something we want to record on a podcast. So let's just say not nearly as evolved as the models that they are trying to bring into the near future. And the near future ones are supposed to be much more intelligent, much more capable of reading your contacts, much more behaving like a human, kind of thing. And so I think that poses the question of when I say how much context and how much repetition you have to put in your prompt to make it do what you want. 
That statement might sound dated in about six months to a year. Because the person listening to it at that time might be like, "What are you talking about? The AI just knows who I am and they just talk to me like a travel agent. It's just normal." But I think in general, what we're going to get is better results, and prompt building in general is going to remain relatively the same. We might get to the end faster. We might get more better concise data. It's going to realize that that great pizza shop is actually closed in Chicago, and it won't recommend it, and things like that. But I think the actual concepts of prompt building, I think they're here to stay for a while.

Mike Gerholdt:
Wow. Well, that's good to know. It doesn't feel like fly-by-night anymore. Well, I'll stick a bow on this episode for now, and thankfully none of our AI's hallucinated.
If you enjoyed this episode, do me a favor and share it with one person, just one. It's not that hard. If you're listening in the Apple Podcast app, you can just tap the three dots up in the right-hand corner, click the share episode, and then you can post it to social. You can text it to a friend and be like, "Let's listen to the prompt building episode together."
If you're looking for more great resources, of course, admin.salesforce.com. The number of people I know that don't know about admin.salesforce.com is hopefully dwindling in the world because I keep bringing it up. But the good news is the reason you can go there, all the resources, if we mentioned any in the show, will be there, a transcript of the show, and links to our Admin Trailblazer group on the Trailblazer Community will be there as well. So with that, until next week when Josh talks to Ravish, and you already had a preview of that episode, we'll see you in the cloud.

 

Today on the Salesforce Admins Podcast, we talk to Chris Zullo, Global Practice Director of Customer 360 and Marketing at AllCloud.

Join us as we chat about integrating Marketing Cloud and Data Cloud and how you can do more with your data.

You should subscribe for the full episode, but here are a few takeaways from our conversation with Chris Zullo.

Bring all your customer data together in Salesforce

Chris is kind of my go-to Marketing Cloud guy, so I wanted to bring him on the pod to talk through how Data Cloud and Marketing Cloud go hand-in-hand. In his role as Global Practice Director of both Customer 360 and Marketing at AllCloud, he’s seen firsthand just how much of an impact Data Cloud can have by allowing both departments to work in tandem.

There are so many applications businesses use in today’s environment that each store data about your customers. But there’s a problem. As Chris puts it, “The likelihood of all of those systems talking to each other in any cohesive fashion is slim to none.” That’s where Data Cloud comes in. It allows you to bring all of that data into one place in Salesforce, and that’s where the magic happens.

Data Cloud creates a consistent customer experience

When a customer interacts with your business, they don’t care who they’re talking to—they just want to be treated consistently and as if they’re the same person. If they had a conversation with a sales rep about a certain product or feature, they expect the customer service rep they call to know what they’re talking about.

With Data Cloud, your customer service rep can look at all the communications a customer might have had with sales so they’re on the same page. And if they notice that there’s an email sequence scheduled next week to remind them about their warranty, maybe they can cancel it ahead of time and head things off at the pass.

That’s why it’s so important to give everyone a seat at the table when you’re establishing Data Cloud at your organization: marketing, sales, service, eCommerce, IT, and your data team. You want everyone working together to create a unified experience for your customers.

Data Cloud makes your data actionable

Some business units get really attached to their data. Sure, they’ll build you an API to provide a one-way glass view of their data, but why do you need them to integrate it with Data Cloud?

“It’s all about making it actionable,” Chris says, “it’s a verb, it’s an action. Just because I have a view doesn’t mean I can do something with it.” Data Cloud lets you do segmentation and targeting at scale without having to copy-paste into a bunch of pivot tables. And with AI features like lookalike segments, the possibilities are endless.

There’s a lot more great stuff from Chris about how Data Cloud can transform your organization so be sure to listen to the full episode. And don’t forget to subscribe to hear more from the Salesforce Admins Podcast.

Podcast swag

• Salesforce Admins on the Trailhead Store

Learn more

• Trailhead: Explore Data Cloud

• Watch: Data Cloud Decoded

 

Admin Trailblazers Group

• Admin Trailblazers Community Group

Social

• Chris on Twitter: @ChrisZullo

• Salesforce Admins: @SalesforceAdmns 

• Mike on Threads: https://www.threads.net/@mikegerholdt/

• Mike on Tiktok: https://www.tiktok.com/@salesforce.mike

• Mike on X: @MikeGerholdt

Full show transcript

Mike:
With Data Cloud, you can organize and unify data across Salesforce and other external data sources. After data has been ingested into Data Cloud, it can be used to drive personalization and engagement through the creation of audience segments. So that's what our help documents say. And I wanted to find out from Chris Zullo, who is a business puzzle solver, Salesforce MVP and Global C360 and marketing practice director at AllCloud. What he's seeing when he's helped other admins integrate Marketing Cloud and Data Cloud and all of the benefits across the organization from having visibility into that. Also, what are some of the questions that admins should be asking in order to get that integration going?
Now, before we get into the podcast, I want to be sure you're doing one thing and that's following the Salesforce Admins Podcast. And the reason I ask is if you're doing that on Apple Podcasts or Spotify or iHeartRadio, then the newest episode will automatically be downloaded right to your phone so you can listen to it on your bike ride or your dog walk, or maybe you just walk around the neighborhood to clear your head. But let's talk about integrating data with Chris and get Chris on the podcast. So Chris, welcome back to the podcast.

Chris Zullo:
Thanks for having me.

Mike:
It's probably been a while, but you're my go-to Marketing Cloud guy, and I feel a lot of people have seen you present in the ecosystem and talking Marketing Cloud. But catch us up. What have you been up to? What do you do? What's your exciting passion in the Salesforce ecosystem?

Chris Zullo:
Sure. So I mean, right now, I am doing a lot of things around Marketing Cloud and Data Cloud as a global practice director for Customer 360 and marketing for a company called AllCloud and just really trying to figure out how best to utilize the data that we have.

Mike:
I love it when you get titles based on marketing and you go, "Had that for a while."

Chris Zullo:
It's a long one.

Mike:
I used to be a director of social enterprise. I was like, "Ooh, that sounds neat." And then Salesforce dropped Social enterprise and I was like, "Oh, now I'm stuck with this." So I'm going to play devil's advocate because Marketing Cloud and Salesforce, I've done stuff, isn't campaigns enough? I mean, as an admin, I signed up my marketing people and they can create campaigns and they can put contacts in as campaign members.

Chris Zullo:
I mean unofficially the campaign object is the first part of the Marketing Cloud going back in time. But no, it is not in fact enough by itself as that is merely just a folder, if you will, a job folder that you can manage any engagement and activities that you plan to execute and engage with your customer base. So yeah, you need to do more.

Mike:
So what do we get when we sit down and have the grownup discussion of let's pull in Data Cloud?

Chris Zullo:
So when you think about pulling in Data cloud or why you would need Data Cloud, you got to think about how many systems and applications store customer data and it's never just one. The likelihood of all of those systems talking to each other in any cohesive fashion is slim to none. So with Data Cloud, you have the ability to connect and create a number of bridges, if you will, to allow all of these systems and applications to feed into one centralized location where we can harmonize, centralize, standardize all of that data to create a unified view of any one individual to better engage with them, to better service them, whatever the topic may be, and not have to swivel chair across multiple systems and try and remove a lot of the manual labor that goes into historically accessing customer data in a lot of different locations.

Mike:
So what are some of the things that you are finding when you work with marketers that they're excited to get data on with Data Cloud?

Chris Zullo:
Well, some of the bigger things are some of the more advanced segmentation capabilities that you're able to do. If you think about from retail businesses that are selling goods or products and they're wanting to figure out what's the customer lifetime value of an individual or how much are they spending with us? Recency frequency and monetary models where you can get into these more robust modeling above and beyond your typical segments of, okay, give me all the people who like the color red. You can get more just deeper into the weeds to create these more robust groupings of individuals that you can then break down into smaller parts as you need. And so, that's one of the bigger things is just really being able to look at that and isolate at scale what people are doing, how are they interacting with us and how much do they really like us?

Mike:
Yeah, how much do they really like us? Dear Marketing Cloud, how much do... Please, no, don't do that. So if I'm listening to this and I'm an admin, I'm putting myself back in those days of sitting in the chair and it's usually an executive or a stakeholder sees something at an event is like Data Cloud. We should talk about that. Where are you finding when you're helping admins or doing some of this work yourself? The admin should start this conversation. Does it start with the marketing team because the marketing team needs to pull that in and then they're going to service? Where are some of these conversations originating?

Chris Zullo:
Marketing certainly has a seat at the table since the concept that Data Cloud is built upon originated within the marketing realm over 10 years ago, the concept of a customer data platform, which really was to make their jobs easier. That being said, they're not the only ones that can benefit from data. So I think if you're going to do it right, you have the right heads of each of the major business units or teams or departments, however you organize your company at the discussion around what do we want to do? Who is our customer? Even before you get to the technology, it's really around alignment across sales, marketing, service, e-comm, maybe IT is involved or if you have a dedicated data team, these are some of the main voices that should have input into creating that centralized model because you may have different uses in each of those teams. The customer doesn't changed and they don't care who they're talking to. They expect to be treated consistently as if they're the same person regardless of the context of what their conversation is on.

Mike:
Yeah, sitting back as an admin where the data's at and that your customer doesn't know where their data's at, they don't get, like when you go check into a hotel, why don't you have all my information? I don't know where you keep all my information. I don't know where my name is stored versus my hotel room preferences and I don't care, I shouldn't because I'm talking to the front desk person. They should have all that. That's a thing that I always seem to forget. So what are some of the conversations like because I have to feel like a few of these databases or wherever this information stored have owners and they own the database. I've worked with orgs before where, yeah, well, IT owns the invoice server or whatever. Boy, they don't want to give that data up. What is the benefit in that? Or they'll come back and say, "Well, I can just write you an API that gives you a view into the order table." What is the benefit of going Data cloud versus a one-way, maybe pane of glass view?

Chris Zullo:
It's really making it actionable. I don't recall the specific quote, but you were in the room with me-

Mike:
Oh, boy.

Chris Zullo:
... back in the day. And it was a difference between a noun and a verb. If you recall the particular event we were at, it was it's all about making it actionable. It's a verb, it's an action. And so, just because you have a view doesn't mean I can actually do something with it. I mean, that's still swivel chair because if I've got to copy and paste or manually key something in that's not making it frictionless, and not only is that making my job harder, that is making the customer experience less enjoyable because that prolongs the conversation that slows down the resolution of whatever activity that individual's trying to carry out. And so, Data Cloud makes it actionable so that once we have that data in, and something that I don't think a lot of people realize is Data Cloud is not overriding those source systems.
It's not a survivorship model. So the systems of record are still the systems of record. The system owners are still in charge of what goes on in their domain. Data cloud is just making it so that we can combine the data from these various systems and make it more usable for business users. And if you want, you can activate or push data back to those systems if you see fit. Otherwise, you're going to activate it into the channels where you can do something with it that's going to benefit the customer and hopefully make your day job a little bit easier.

Mike:
So what I'm hearing is, as a marketer because that's where we started, I can query contacts and with Data Cloud also look at maybe contacts with invoices greater than a $1,000 and not have to do a pivot table with contacts I pulled out at Salesforce and then invoices that I got out of this other system because the data is actionable within Salesforce.

Chris Zullo:
That's absolutely correct.

Mike:
Just letting that moment of silence kind of fall upon people as you hear 10,000 pivot tables in the background screaming, because I feel like that. It's a different scenario, but I remember just Salesforce a long time ago used to be able to do web tabs or whatever. And so, I set up a web tab, which was our travel portal, and I remember the salesperson being like, "Oh my god, Mike, this is amazing. So this means that when I booked the travel, it's going to put it on my calendar." And I was like, "No, it's just a pane of glass to our travel portal. It is just that there is no integration."
And too often I think people get caught up in what the visual looks like. You asked for order information, so here it is on another tab when you click this and now you have access to it. Except as a marketer, I still have to go to this other system, to the invoice domain on this other server and pull customer numbers and pull contact records and then pivot table the two as opposed to using a report in Salesforce or something in Tableau to create that campaign.

Chris Zullo:
That can be a brutal way to go about things. And frankly, a lot of us have been used to that for so long because that's just the way it was done. But now there's a better way to utilize that data and like I said, make it more actionable to speed up the process and the time to value both for the business as well as the individual that you're supporting or trying to provide great customer experience to. So another example of that is you mentioned orders, but think about from a case perspective, and this is going to touch across multiple teams. If somebody calls in with an issue or have questions about a product or service that they've bought, so you have the customer service rep on the phone, there was an order placed and fulfilled at some point in the recent memory.
And you may have active marketing communications going out to this individual on a regular basis. And so, that's just three teams that could be involved in that one call. And so, in that moment, does the customer service rep know what you have bought recently without having to ask and make you repeat 15 times after they've done that to validate that you are who you say you are? But then can I see your order history? Can I see that there's some marketing communications scheduled very soon that might be touching upon this very same topic or related topic, which maybe we let go? Maybe we want to hit pause for a second and say maybe we don't want to hit them up with this marketing communication because they've called in, they have a question, we haven't resolved it.
It may or may not be negative, it may just be a neutral situation, but we don't want to potentially turn this into something bigger than it is. And so, you've got those three different teams that can be influenced by that one call, but how many systems does that rep have to go to see what this person has, what they have bought, what email communications are coming up, or SMS if it's a different channel? All of that can be in one view if you are able to unify everything through Data Cloud.

Mike:
Yeah, I always feel like the conversation with marketing is sales oriented, but the real increase in fidelity is when as an admin, marketing and service talk to each other, because that's normally where the joy can be maintained of the sale. After the salesperson not walks away, but closes the deal, to your point, if they have say, a warranty issue, the last thing they want is two days later after a customer service call to get a marketing email reminding them to sign up for a three-year extended warranty. Like, "Hi, welcome to Tone Deaf Marketing." But it happens, right? And I always feel like when you sit down with marketing people, their initial inclination is sales oriented. But I feel like what I'm definitely hearing is a big value comes to the customer service rep who is, "Hey, I hear you. Let's work through this issue. I see you're on a couple of warranty reminder emails. I'm going to go ahead and uncheck you from those." And you can correct me on this, the marketing team, empowering the service team to do something like that, right?

Chris Zullo:
Yes, exactly. Work smarter, not harder.

Mike:
What are other examples that you're finding of, I won't say it's unintended, but unintended collaboration like that unlocked because of Data Cloud?

Chris Zullo:
Sure. So I think other ones is to your point, from a sales perspective, sometimes people lump marketing and sales into the same team oftentimes and stereotypically and very humorously, it's like Westside story and they're on rival factions where we agree on nothing.

Mike:
I would love to think that every sales and marketing meeting begins with teams snapping at each other.

Chris Zullo:
Oh, I feel like there's a nice skit in the future with that one.

Mike:
There is.

Chris Zullo:
But so think about how those two can be working more collaboratively whether they want to or not, they should be. But thinking about you have people selling on an interactive basis, and if you are, say it's multithreaded in its account-based marketing, and you have different sellers talking to different people in the same organization, do they know that?

Mike:
Oh, yeah.

Chris Zullo:
Do we know if the left hand is doing while the right hand's over here shaking a new hand? How are we connecting the dots not only internally, but also looking at the target organization? Who is getting what communications? How are we bombarding them with all these different communications? Or potentially, do we want to empower the sales team to drop somebody into a nurture campaign? It would be a lot more effective if A, we can bubble up the fact that, okay, we have one organization, we have got two sellers talking to five different people and they're on all these different communications. One's not.
And then we can look at a broader picture from an account level at the individual level and internally who's doing what, when, where, and why. All of that rolls into how can we provide a better service from a sales perspective, and how can we empower bidirectionally marketing and sales to help each other to put them into the right communication? Or maybe again, similar to the previous example, maybe dial it back. Maybe we don't want to hit them as much because they're talking to a human being. We don't need to prompt them to schedule their next appointment.

Mike:
Right. Yeah, that's always fun when you're getting the email. So moving ahead, AI is a thing, it's been a thing for a while. We have Prompt Builder, we have Einstein Copilot. What are some of the cool things that you're hearing marketers are really looking forward to with some of the AI stuff that's out there?

Chris Zullo:
I think some of the predictive capabilities, I think really being able to leverage the AI from an ideation perspective, creating content or I don't know about you, but I do enjoy writing, but I don't always hit the ground running and wanting to be able to throw an idea out there, get something back and go, okay, that's not exactly what I wanted, but I can work with this. And so, then I can tweak it. And so, I might have a great idea, but I don't have the words to get it going. And so, that's one example from a marketing perspective. The other is from a data perspective, thinking about, again, the data has a story to tell and the better your data, the better the story can become.
And with AI in particular leveraging good data, we can then identify trends or identify opportunities that maybe we're not looking at as closely as we could or should, but also would take us a lot more time to effectively do if we were doing it manually and allowing that to create a lookalike audience, a lookalike segment to say, "Hey, here's your best audience based on these parameters. You've got this whole group of untapped potential that would potentially be really interested in this same product or this same service, but you've never bothered to ask."

Mike:
Yeah, I mean, you put a lot on the salesperson to make those connections in their head, and sometimes it's just not going to happen depending on the salesperson, right?

Chris Zullo:
Exactly.

Mike:
This is more of a Mike question because Mike's curious. So where are marketers falling with a lot of the advancements in AI writing emails to customers? Because you and I, we're from the days when marketing had to go over every single letter word, consonant vowel period in an email, and we built email templates and we would build workflows with email templates. And somewhere a marketer would lay his head down or her head down at night and be like, "I know exactly word for word what the customer got when we closed the deal." But now with AI we can kind of say, "Hey, tone and voice..." And maybe be softer or maybe be happier or funnier. And I suppose it's no different than just letting people write emails, but I'd be curious kind of what you're hearing because I feel you're a little more plugged into marketers than I'm.

Chris Zullo:
Yeah, I think there's a relative split. I think you've got a number of folks who are embracing it and leveraging it for the benefits that it offers. I do feel that there's still a bit of skepticism and fear. And to be honest, two years ago I was very much skeptical on what AI was going to do for me as a marketer. So I decided to investigate a little bit further and learn more about it and saw that there really is a lot of potential with AI. And I think the way I would explain it is AI is not going to replace you. I think people who understand and learn how to harness the power of AI are going to have an inherent advantage over others because it is a productivity play, in my opinion. And so, the way I have been explaining it to people is it's not so much artificial intelligence, but it's supplemental intelligence. You don't replace the human. The human still needs to be involved. You're still the chaperone. You still going to be a hand on the wheel, but it's almost like having Jarvis from a very popular.

Mike:
[inaudible 00:25:27].

Chris Zullo:
Yes, our boy, he is a helper, but he can't do all the things without your guidance. Jarvis was a product of Tony. And so, the AI that we're using in our organization, it's really going to be a product of how you utilize it to increase your time to [inaudible 00:25:54], your speed to market, or reduce the friction to process data. It's really about taking that and leveraging that in a way to be more efficient with the time that you have and still have the final say. I'm not asking Einstein to create an email and just send it blindly. No, I'm doing it to jumpstart the process and then I can refine it and revise it with a trained human hand that knows, you know what? That might not work the way that the output provided it. And you can either train it to get better, which it can do, but at the end of the day, it still requires you or me to be involved in the process. It doesn't work asynchronously. It just doesn't.

Mike:
Yeah. I was talking with a friend this weekend, and of course, this'll date me in 10 or 15 years, he's a professor at university. He said, "AI's not going to take your job. What's going to take your job is the people that know how to use AI."

Chris Zullo:
Exactly.

Mike:
And I was like, "Oh, you're so spot on." We diverged a little bit. Last question, anyone who's looking to get interested in Data Cloud, what would your suggestion be?

Chris Zullo:
I would jump on Trailhead for one. That is a great place to start because you can get hands-on exposure and experience. And honestly, whether you realize it or not, admins, you have such an important role in your organization and Data Cloud can have such a significant impact on how your data is managed, that it really is in your best interest to understand how it works, how it can impact your environment and how you can influence it. And so, number one, go to Trailhead and get started there. There's a number of resources out there. I'm trying to think of the name. There is a great YouTube series that Danielle Larregui oversees, the specific Data Cloud series and has a number of different guests from Salesforce on there about how Data Cloud works and how to use some of the various features within that, and it's a really good resource.

Mike:
I like it. Thanks for coming on the podcast, Chris. It's always good to hear from you and I'm sure we'll hear some crazy visionary insights from you at Dreamforce this year, right?

Chris Zullo:
I will certainly be there. I've been around for a while, so I don't know if anybody really wants to hear from me anymore, but I'm always happy to share.

Mike:
I don't know, I got to believe so, right.

Chris Zullo:
Hey, I'm willing and ready. If the invite's there, I'll be there.

Mike:
I appreciate it. So it was a great discussion with Chris I, You always think of what's the immediate benefit of doing something with another cloud? So what will Data Cloud get sales? Or immediately, as you heard in the conversation, my head goes right into marketing and sales, but there's also a lot of other benefits that other departments are seeing and we had that discussion about service, how you can actually talk and service your customers better. Having that integration, that information, it just kind of makes sense. So I hope you enjoyed the episode. I thought it was a lot of fun.

Today on the Salesforce Admins Podcast, we talk to Joe Sterne, a Solutions Architect and Salesforce contractor.

Join us as we chat about his tips for job interviews, what to look for in a job description, and how you can use AI to help you prep.

You should subscribe for the full episode, but here are a few takeaways from our conversation with Joe Sterne.

Contract work in the Salesforce ecosystem

Last month, we talked to Jason Atwood about how to prepare for a Salesforce job interview. That episode was fantastic because Jason interviews job candidates all the time, but I wanted to hear from someone who’s had experience sitting on the other side of the table. That’s why I was so excited to hear from Joe Sterne about his experience as a contractor.

Contracting is becoming more common in the Salesforce ecosystem, and it can be a great way to get experience to land that next-level position. “At the end of the day, certifications are great,” Joe says, “but certifications aren’t the be-all, end-all—it’s also experience.” Of course, being a contractor means that you’re constantly looking for that next gig, so Joe has a lot of great tips to share from going out on so many interviews.

What to look for in a Salesforce job description

Looking for a new position usually starts with reading through a bunch of job descriptions. Joe recommends taking a close look at what responsibilities are actually listed because it doesn’t always match the job title. It can happen for any number of reasons, but it’s important information to know going into the interview process because it can affect the salary band.

Joe also suggests investing the time to make sure you have something to talk about once you land that big interview, especially if you’re bound by an NDA. It could be Superbadges, or work you’ve done for a nonprofit, or, as Joe says, “maybe it’s something you did for fun just so you could talk about it in an interview.” No matter what, you need a way to demonstrate your skills and knowledge and how they’re a fit for your new role.

How to prep for a Salesforce job interview

When you’re prepping for an interview, Joe recommends taking some time to learn about the business and the industry they’re in. Who are their clients? What problems are they trying to solve? And, most importantly, why are you a good candidate for them to help them address those problems? At the end of the day, that’s what you’re selling.

As Joe says, you want to be able to walk into the interview and say, “Here are your problems, I understand them, I’m going to be able to fix them, here are some ways I should be able to fix them, and here are other ideas I have that I could work on with other people as I learn more to evolve those solutions.”

There’s a lot more great stuff from Joe in this episode about how to deal with weird interview questions and how he uses ChatGPT to help him prep, so be sure to listen to the full episode. And don’t forget to subscribe to hear more from the Salesforce Admins Podcast.

 

Podcast swag

• Salesforce Admins on the Trailhead Store

Learn more

• Listen: How to Prepare for a Salesforce Job Interview

• Listen: Being Neurodivergent in the Salesforce Ecosystem with Joe Sterne

• 5 Ways to Make Your Sales and Service Reps’ Lives Easier with AI

 

Admin Trailblazers Group

• Admin Trailblazers Community Group

Social

• Joe on Twitter: @MrJoeSterne

• Salesforce Admins: @SalesforceAdmns 

• Mike on Threads: https://www.threads.net/@mikegerholdt/

• Mike on Tiktok: https://www.tiktok.com/@salesforce.mike

• Mike on X: @MikeGerholdt

Full show transcript

Mike:
So let's say you're out there as a Salesforce admin and you're interviewing and you get a crazy question like, "If you could be any animal, what animal would you be?" Well, I won't tell you the answer that Joe Sterne gave but Joe Sterne is on the podcast today and he's going to help us flip on the other side of the coin. That's right. So it's June. If you remember back in May, I had Jason Atwood on the podcast. He's from Arkus and he was talking about what he does to interview Salesforce admins. My hope was to get you in the mindset of what a hiring manager is looking for.
Today, I got Joe Sterne, who is out there in the job market and he's interviewing as a Salesforce admin, at least he was at the time that we reported this. And gave some tips to help you get ready for your interview, some things that he's doing. Also, you know what? We talk about contract work because I think that's a very viable solution as a new admin. Now, of course, before we get into the episode, I want to make sure you're following the Salesforce Admins Podcast wherever you listen to podcasts, whether it be Apple Podcasts or Spotify or iHeartRadio. Go ahead and click that follow button and the reason is then a new episode will be put on your phone right away when you wake up Thursday morning. So with that, let's get to our conversation with Joe.
So Joe, welcome back to the podcast.

Joe Sterne:
Hello.

Mike:
Good to have you on again. It's been a while. But let's talk about, so back in May for the people that follow along with the podcast, because I know everybody does. I published an episode How to Prepare for a Salesforce Job Interview in 2024 and Jason Atwood was my guest. And I think he did a really good job of prepping us on the employer side. You, I know, are currently now on the admin side. So I wanted to get the... Does it show my age if I say the peanut butter cup scenario, like the chocolate and the peanut butter version?

Joe Sterne:
I mean, I don't think so. I'm still a big fan of Reese's Peanut Butter Cup. Wait. Can I name drop brands on this?

Mike:
Yeah. You can.

Joe Sterne:
So-

Mike:
I mean, if they want to want to send me a care package of peanut butter and chocolate, I'm all for that.

Joe Sterne:
There you go. Yes. I mean, to me, that does not date you. If you were saying something more along the lines of... I'm trying to think of... Not Milk Duds. There's some candy that's coated in chocolate that has powder in the middle of it that's from the 1940s.

Mike:
That's Milk Duds. That's Milk Duds. Every time I've had Milk Duds-

Joe Sterne:
Oh, okay.

Mike:
Oh. No, no. Malto-

Joe Sterne:
Malt... yes. Malted Stuff. Yeah.

Mike:
Malted Dots or something they're called.

Joe Sterne:
Yes. Yeah. Those-

Mike:
Yeah. Those things-

Joe Sterne:
Are old.

Mike:
You bite into it, you're like, "Oh, chocolate," and then it's like a puff of dry dust.

Joe Sterne:
Exactly. Yes. That, I feel like, would date you.

Mike:
Wow. All right. So Joe, since we've last spoke, what have you been up to?

Joe Sterne:
Oh man. So was I still at Salesforce when we last spoke? I think I might have been.

Mike:
You were still?

Joe Sterne:
So yeah, I was wrapped up in part of the layoffs in the beginning of 2023 and landed a couple different solution architecture specific roles at companies over the course of 2023 that also had layoffs sadly. The market has been quite chaotic over the last year and a half in the Salesforce space. I am currently right now doing contract work for another company, still doing solution architecture, but doing it under my own LLC.

Mike:
Ah. So what have you found interviewing... And I guess being an LLC and pitching consulting services, you're interviewing, right?

Joe Sterne:
Right. Oh, yeah. Yeah. You're still interviewing. It's just, to me... Well, I'll take one step back here. I'm still interviewing for full-time or W2 positions as they like to call it when I've been talking about positions but I'm also open to 10-99 or corp to corp. Corp to corp is one of the main reasons that I decided to do an LLC. Besides the tax reasons, it's the ability just for somebody to come back to me and be like, "Hey, we can do contract but it needs to be corp to corp." It's like, "Cool. We can do that. I have one."

Mike:
Gotcha.

Joe Sterne:
And not have that be a limitation where it's like, "Hey, we can't do 10-99 or W2 on this engagement," that knocks you out of the rutting. It's like, "Well, okay, that doesn't really help me and I would love to be able to deduct stuff from a business standpoint. Since I'm going to be using my own hardware in most of these contract situations, I'd rather just wrap that up from a business perspective." So I know that's not necessarily totally viable for a lot of people, especially just starting out in the industry. But I would say, it's something to be aware of because I have seen a pretty big shift within the last 18 months in the industry. Well, big for me. I've been in the industry since 2013 and I fell into it. That there's been a dramatic increase in contract roles of any sort and a pretty pronounced pullback in full-time W2 roles.

Mike:
Okay. But let's tackle that first part. Let's say you are, for your opinion, a newer admin. What is the level of experience you feel people should be at before they would go and do what you did which is start an LLC and do, we'll just call it contract admin work, as opposed to being hired on as a position within the company?

Joe Sterne:
Yeah. I would recommend probably being at some sort of a senior level, so a few years of hands-on experience ideally. That you can then use to translate some of the value of why you would be a good candidate for them from a hiring role in general, whether it's contract or not. But here's some of the stuff that I've done, here's some of the things that I'm a part of, here's some of the knowledge that I have, that I've encountered on the job, some stuff that I may have not necessarily encountered on the job but dabbled in.
Because at the end of the day, certifications are great. I am a certification ambassador for Salesforce so I will not say anything different. But obviously, certifications aren't the be all end all either. It's also experience. Experience both helps you get a certification as well as certifications help you get experience. So it's this chicken and the egg scenario sometimes when you're first starting out where it's like, "How do I get that experience if no one's willing to take a chance on me?"
That is obviously a much larger conversation than what we're having today. But having some of that experience, I think, is helpful if you're trying to go that contract admin route or a fractional admin. Which I feel like as the rise of some of these C-suites, I think that some of that "fractional work" may start coming up where you may be working for two or three companies at once. That you're all doing admin things, but they just don't have the level of requests or tickets or change that would require somebody to be on full-time with benefits but they still need some help.

Mike:
Right. That may be the case, right? In your area or depending on where a person is, maybe they're not hiring for a full-time admin. So you're newer, you need the experience, would you take on a contract role? Let's say a company's like, "Look, we're not going to hire for this position full-time but we will do a 6-month contract with you." As an individual, to me, that sounds like a great way to at least get some experience.

Joe Sterne:
Absolutely.

Mike:
And then you're also working towards, "Well, they could renew the contract. It also gives me a few months to get in with an organization," and maybe you may like it. And then, you could... Well, if you made this full-time, look at all that you would get.

Joe Sterne:
Right. The one thing I've seen over the past few months as I've navigated the new contract world. Because historically, I've only looked for W2, but with this market I've had to open myself up to contract roles, is that there definitely is the concept of contract to hire.
Where essentially instead of testing out an employee for 60 or 90 days, you're essentially testing them out for six months, a year, or so. Some of those offers might just be dangling in front of you to get you to be willing to do a contract. But I feel like others actually do convert and drawing some parallels to outside the Salesforce ecosystem when it comes to community management or marketing, having a bunch of contract roles before you land a full-time one is not unusual.
It used to be unusual in the Salesforce realm and I feel like that is also starting to change just with the way that the current market is and the pullback on head counts. That is forcing companies to arguably prioritize their bottomline over their employees. But again, slightly separate conversation. But making sure that from a cost standpoint, that they're not necessarily wasting money on separate groups that they don't "need" too.
So I think that having the ability to grab a contact role for six months is great. It's just that one of the things that you will need to be aware of is that from a interviewing perspective, you don't... Sometimes when you get a full-time job, especially if it's one that you've been pining for, for a while, you take a step back from the LinkedIn and the job application market for a period of time.
When it comes to contracting like sales, you don't really have that luxury. So yes, I am currently contracting for one company but I've never stopped looking for additional work. Just because I don't necessarily have an exclusivity with my current company and I'm also... I'm trying to get to 40 hours a week billable right now which they can't offer and that's okay. It was only pitched as part-time anyway. But for me, it's always trying to find more work and more potential pipeline.
So it's very similar. It's from a consulting standpoint of trying to build a book of business and trying to build a pipeline and trying to line that up. Because ideally, if I stayed in this world of contracting work and whatnot, I would be trying to make sure that I'm fully booked out for a year or so in advance and turn away work or refer work to other people rather than trying to scramble for it. It's the typical feast or famine concept.

Mike:
What were... I guess I started in the past tense. But what are some of the things that you do when getting ready for a job interview, either as a W2 or a 10-99, that you feel is applicable to a lot of admins?

Joe Sterne:
Oh, man. So I would say, one of the things that I've really started to leverage. And I know that the whole AI, AI, AI thing has been beat over-

Mike:
Really? You don't get that anywhere? I haven't-

Joe Sterne:
Yeah. No, I-

Mike:
I haven't seen AI anywhere. That's the first I've heard of it.

Joe Sterne:
Yeah. Exactly. Over the last year, I've definitely started to leverage at least ChatGDP more and more to a point where I'm actually paying for it. I tried to actually set up my own custom GDP around Salesforce architecture that got kicked off the store because it used the term Salesforce. But that is something that I've found to be helpful when I have been, A, researching the company and the industries that company is in. Because asking questions about that, diving deep, granted for most of the stuff that people think of AI today, arguably it's just spicy autocorrect.
But there are some areas where it can definitely start doing things for you that are either tedious or just time-consuming. So I just saw an article that Shannon Tran posted around a Salesforce Ben posting where they were trying to implement different types of AI in an org and they were just trying to figure out what made sense. It turns out, a lot of it, they had to go off platform for and that brings up a ton of complexity. As an admin, you're not necessarily required to know all of that. But you would want to know at least on the Salesforce side, what they're planning on doing and what tools that they are implementing. And what different areas or different features that may have not been available in the past are now available. Is the company going to be paying for those extra licenses? How are those going to be implemented? Are you implementing them? Is a third party implementing them?
So there's a lot of different questions that would probably come up in an interview if you start diving down into that. I have found that tools like ChatGDP are very helpful to navigate those flows beforehand and potentially, give you a talk track before you actually even talk to them. So I mean, you can use ChatGDP as a pseudo interviewer and have it just drill you for questions. You can use it as a certification prep tool and have it ask you questions.
Now, granted, especially in the latter example, I would want to verify that those answers are correct because they do have the chance to hallucinate every now and then. Obviously, I always joke that because it's on the internet, everything is true. But I do feel that when people see things that are typed out, they usually default to thinking that is true rather than potentially critically thinking that it may not be. So just a word of caution that you may not have 100% accuracy in truthfulness. But, to me, that's been a great way to prep for interviews just because I can almost have a conversation rather than me just doing a few Google searches and having to potentially connect the dots here and there which is also very useful.

Mike:
You said something that... Well, right at the beginning of your answer, it's been just echoing in my head that I want to know in the current landscape... You said, "When I'm looking at a company and how I would work with them..." How much does that come up in the interview? How important is it in the age of the internet that you actually do the prep work on the about page and the history page and the about us page or if they have a corporate values page? How much do you do that when you're prepping as an individual or as a consultant?

Joe Sterne:
So I would say that you don't necessarily need to know their entire executive suite by the back of your hand and be able to recite off what they've done like you're talking about a sports player. Unless you want to, by all means, go for it. I've found that knowing a initial amount about what the industry that they're in, some of the customers that they deal with, whether that's other businesses, whether that's end consumers, whether that's both, it helps you figure out some of the problems that they're searching for.
Because eventually, that's what you're trying to help them solve. That's what you're selling to them as a solution is, "Here. Here are your problems. I understand them. I'm going to be able to fix them. Here are some certain ways that I should be able to fix them. And there are other ideas that I have that I could work with other people as I learn more to evolve those solutions." I mean, that's true if you're a consultant, that's true if you're in-house. You're there to solve problems and make the company money or make the company money by making other people more efficient, stuff like that.
So having a baseline knowledge of what they're doing helps you because from an initial interview standpoint, you may not necessarily have a lot of the... The best way to describe this is like a contact situation where it's, "Hey, given this certain issue that we're having, we're going to give you a quick brief background, tell us how you might approach it or tell us how you might solve it." I see that all the time. Those, if you don't know what the business does, you don't know how they necessarily act with their clients or partners or anything in their ecosystem, it's going to be a struggle for you to answer those. Because you won't know that off the top of your head and then you might have to fumble your way through it.
As opposed to doing a little bit of research, not a ton. Because granted like right now in this market, I've found that there is a lot of quantity that you may have to go after initially before you can start focusing on quality as those amounts of interviews narrow as you go through the process. So it does take a lot of time to fully memorize a company. I'm not recommending that you do that. But not knowing anything about them and going in "cold" is not going to help you either because you won't be able to answer those hypothetical situations.

Mike:
Right. Yeah. It's funny just having been in the world and seeing that change, just the difference that the internet brought interviewing people. God. Before times? So what are things that you... Always, we get asked, and a lot of people get asked like job description. What should I look for in a job description? How do I know if this is... Is this a Salesforce admin job? Some companies call it that. They call a duck a duck, you're a Salesforce admin. Some don't. The business technology specialist or corporations sometimes have different naming conventions. What are things that you look for in job descriptions?

Joe Sterne:
Okay. So-

Mike:
Buckle up. I feel like this is an answer.

Joe Sterne:
Yeah. So it's funny that you bring this up because from the one thing that I have definitely noticed as being a solution architect, for the last half a decade or so, is that a solution architect these days isn't always a solution architect. You have to actually read the job description. Because a lot of times, I've encountered where you have a "solution architect", like that's what they call you. But you're asked to do Apex coding and debugging and all these other things that a technical architect would be responsible for.
I don't know if it's just people don't understand that there is a fairly clear delineation between technical architects and solution architects when it comes to the amount of code that they should be required to do or if they're just trying to get a technical architect for cheap. Because arguably, the pay band for a technical architect, like any other dev, is a little bit higher than a solution architect which is generally not responsible for stuff like that.
So I have seen a lot of that confusion in the marketplace when it comes to the position that I'm currently in. And I think that definitely also cascades down into even the difference between a "junior admin" where they're asking you to do everything an admin would do, but they're only trying to have you at the junior level to save cost or that they may not know better.
It definitely depends on, if you can tease out, how long they've been using Salesforce. Because obviously, the newer they are to Salesforce, I think, the more struggle of understanding titles and how they reference to typical other titles in the ecosystem. It's a little bit more of a struggle if you've just started Salesforce as opposed to, "Hey, we've been on Salesforce for a decade. HR is caught up to this. We're well aware of pay bands. So that's not something that we're going to necessarily be able to," I don't want to say con, but, "argue with the level of talent that we want."
Because that's something where if you're applying for a job that says junior and all of the stuff that they're asking and all the things that you talk about in the interview says, "This is actually a typical admin or a senior admin level," that's something to call out. Because that's probably going to show up, maybe not necessarily on the title side, but it's probably going to show up on the pay band side.
So being aware of what a typical admin is responsible for is generally pretty helpful when you're reading these job descriptions. Because then, you can get a gut check of like, "Hey, are they really asking for an admin or are they asking for a senior admin? They just happen to have it marketed as something different."?

Mike:
Yeah. Well, and a lot of times, a lot of what we find and this is true for a... I don't want to pick on just admins because I know I've talked to the developer relations side. It's that way, too, with a lot of roles that people write. Especially if it's a new role within the organization, they just blanket, "Here's everything you should do," and it's like... I remember reading job descriptions in... Was it 2017? And they said, "You need five years of Lightning experience." It's like, "Well, it's only been out for two." And it's no fault to the company, they just... I don't think they somehow know to categorize stuff like that. So yeah, job descriptions can be all over the place.

Joe Sterne:
But as long as you're comfortable with what they're asking you to do, at least on the ten, that is usually a good start. Because the other thing to note about the job descriptions is it's generally, not always, but it's generally a starting place to some of the questions that you're going to start getting from the interviewers. One of the things that I get all the time when I am pitching companies or just interviewing generally is they're like, "Hey, you gave me an example about X, Y, Z. Can you go into more detail?" It's like, "No, I can't. I'm under NDA, so you can go talk to this company and have them sign a waiver if you want but I can't tell you exactly what I did. I can tell you that I worked on it."
That happens more often than people think because they're trying to not necessarily see what the competition is doing but they're trying to gauge your skills. So being able to have ways that you can talk about your skills that aren't necessarily bound by an NDA can be really helpful. Maybe, that's some stuff that you've done with Superbadges, maybe that's something that you've done with a nonprofit that isn't necessarily bound by NDA, or maybe that's just something that you did for fun, literally, so you could speak about it in an interview. There's nothing wrong with that. But those questions generally do come up. It may not be first round. It might be second or third. And God, hopefully not fourth or fifth. But those-

Mike:
You never know.

Joe Sterne:
Yeah. You never know. Those examples usually directly relate back to that job description. Because there are people that you may be talking to that aren't necessarily very close to Salesforce. But they're brought into the interview process because they are a department that you're working with or a division that you're going to be embedded in. They may not know everything about Salesforce, so they may just go down the job description part and ask you questions.
They may go down your resume and just drill you on, "Hey, why do you have this on here? Can you tell me a little bit more about it?" So being able to say, "Oh, cool. Thanks for asking me about that here. And I'm going to go into a 2-minute monologue of the question that you just asked." That's definitely very helpful because it shows that, A, you understand what they want and you also understand what you've done and you're able to talk about it at arguably a snap of your fingers. And not necessarily have to be like, "Oh, well, hold on a second. Let me look that up," and, "What did I write here?", kind of thing

Mike:
As we wrap things up, I... It sounds like a fun question. Fun is a word that means a lot of things in my head so we won't use-

Joe Sterne:
Are we using air quotes right now?

Mike:
No. I'm trying not to. Nobody can see them. Let's use the word interesting.

Joe Sterne:
Okay.

Mike:
What is the most interesting question you feel comfortable sharing that you got in a job interview?

Joe Sterne:
Oh, man.

Mike:
See how fun could also work?

Joe Sterne:
Yeah. Yeah. Fun could also work. I feel like that is... I've gotten a lot. I've had a... So I would say within the last year and a half across the last few jobs that I've gotten ever since I left Salesforce, I've probably put in well over a thousand applications.

Mike:
Wow.

Joe Sterne:
I've had not a very good conversion rate to interviews but I have had some interviews. I think that the more bizarre questions that I get are usually something that has absolutely nothing to relate to Salesforce. I think it's the ones that they're trying to figure you out from a psychological perspective but they haven't really thought it through. So it's the ones where it's like, "Hey, if you could be any animal, what animal would you be?" "I don't know. An elephant? So I can't forget all this stuff." Like, "How does this relate to what we're doing?" That was-

Mike:
Joe, how are you going to type with elephant feet?

Joe Sterne:
Right. Exactly. I'm like, "I'll have to use-"

Mike:
[inaudible 00:29:30].

Joe Sterne:
Right. I'm like, "Do I need to ask for accommodations here?" So it's questions like that, that I've gotten, where it's just been completely oddball. Like, "This has nothing to do with the job at all. How..." I even struggle to how connect the dot back to the interview process itself where it's like, "Hey, what are you trying to ask me?" Because it's not something simple of like, "Hey, I'm having this issue. How would you tackle it?" It's like, "Well, I'd try to do it in configuration and this is the way that I think I would tackle it based on this information. If that changes, then maybe I'd look at the App Exchange and see if I could find anything there. If that didn't necessarily work, then I'd have to start talking about custom code and understanding..." That's a whole train of thought that you can have with a question that is semi-technical related. But if you have somebody asking, "Hey, what brand of soda would you be and why?" Where do I go with that?

Mike:
Yeah. First of all, you've got the big two. And then, what if you go a regional flavor that nobody understands with limited distribution?

Joe Sterne:
Right. Or what if you go something retro like, "Hey, I'd like to be Tab or Crystal Clear Pepsi," like-

Mike:
I was going to say Crystal Pepsi, yes.

Joe Sterne:
Yeah.

Mike:
That's the second or third time it's come up on this podcast. It's awesome.

Joe Sterne:
Yeah. I mean, bringing it back full circle, talking about something that will date you, Gen Z has no idea what Crystal Clear Pepsi is. But it is definitely one of the, I would say, the rare failures of soda, up there with new Coke which is also-

Mike:
It still doesn't... Coke still doesn't taste right. I remember what Coke tastes like as a kid and the whole new Coke, new Coke tasted like Pepsi.

Joe Sterne:
Yeah. Exactly. They were trying to go after the sweeter market. I only remember this because Stranger Things did a Coke tie-in, I think, for Season 2 or 3 where you could buy redone new Coke in the can. And so, I bought it just to taste it and I remember sipping it and I was like, "This is horrible. This is knockoff Pepsi, store brand Pepsi." And I was like, "Yeah. I can see why this didn't go anywhere."

Mike:
Right.

Joe Sterne:
So yeah, so I would say that I don't know if you could necessarily prepare for those questions of, "If you were a soda, what soda would you be and why?" But those are usually ones that I would found there, it's like, "All right. Maybe I should reconsider wanting to work for this company in general if you're going to be asking me questions like this. Because I don't know if this is going to be a reflection of the type of company that it is too."
Because I mean... I feel like one thing that a lot of people forget, and it's easy to especially when you're desperate for a job, is that you're also interviewing the company. You're trying to figure out if you want to work there too. So there are times where the interviewers are trying to sell you on working there and there are times where they may not be. But that's something that, ideally, is on you to figure out, "Hey, I need to be able to ask questions that would determine if I want to work there," and those can vary from people.
So I can't say there's a list of questions that you should ask every company, period. But a very good one to start teasing out how they were is what is their stance on return to office? Because that's usually a really good indicator of, "Do we listen to our employees actually or do we say we listen to our employees and ignore them?" So it's questions like that... Obviously, if you want to be in the office full-time, you can ask that question. It doesn't necessarily matter what they say. But if you don't want to be in the office full-time or if this was marketed as a remote job and they're actually saying it's hybrid, that's something to think about like, "Hey, if they can't get this right in the job application, what else are they going to potentially be getting wrong or not necessarily telling you the truth when you're working there?"
So make sure that you don't forget that you're also interviewing them to see if they're a place that you want to work for too. Not necessarily just... It's not one-sided. It's always two sides of a conversation. It's a conversation. It's not a monologue. It's something where you need to have back and forth and it's for the... Ideally, it's for both sides to make sure that, "Hey, we're both in agreement of what's expected."

Mike:
Yep. I completely agree. I wasn't trying to teach admins anything out of this other than just sometimes getting funny questions is a fun way to end things. Joe, I want to thank-

Joe Sterne:
Oh, yeah. Yeah. Sorry. I probably went on a serious tangent there.

Mike:
No, you're fine. We know you want to be an elephant.

Joe Sterne:
Yeah. I mean, sometimes that's also to keep with a funny thing like, "Do you have any questions?" That's also something that you can just throw back at them too. "Hey, if you were a soda, what soda would you be and why?" Because I guarantee that 99 point something percent of people aren't expecting that question. So it's a... Depending on the banter that you have with your interviewer, it might be a fun way to end it out.

Mike:
Right. Good. Joe, thanks for stopping by and-

Joe Sterne:
Of course.

Mike:
Keeping us up to date on what's going on out there. If people wanted to follow you on anything social, I'll go ahead and link it down in our show notes.

Joe Sterne:
Yes, that would be great. Yeah. You can find me on Twitter, I refuse to call it X. You can find me on LinkedIn and I mean, heck, you couldn't find me at my new company. You can shoot me an email. Feel free to reach out to me. I still have people reaching out to me from our past conversation I've had on this podcast periodically so I always love to get those notes. Yeah. I love to get those notes because I mean, I'm here to help other people. So if I haven't helped you, I'm sorry. That was definitely my goal of today. And if I have helped you, I'd love to hear that I have because it's always a nice ego boost.

Mike:
Absolutely. Thanks so much, Joe.

Joe Sterne:
Thank you.

Mike:
It was a great discussion with Joe. I'd love to know, so what answer would you be for an animal? The whole time that he was asking that question, for some reason, the tiger came to mind. But I'd be curious, I'd love to know what animal you could be if you were a Salesforce admin at a job interview. But I did think that Joe gave us some really good tips and from an experience standpoint, oftentimes, it's brought up, "Go help a nonprofit." But sometimes looking for a full-time FTE job versus a contract job, a contract job might be a good path for getting some experience. If it's a trend that a lot of organizations are going to, it's a great way to get into the front door of that organization. So thanks, Joe, for being on here and sharing some of those wisdom.
Now, if you're doing one thing and you enjoyed this, I want you to help share and spread the word. So if you're listening on Apple Podcasts, just go ahead and tap the three dots in the upper right and click Share Episode. What you can do there is you can post at social or you can text it to a friend, maybe you have somebody else that's out there looking for a job. Of course, I mentioned resources, links to Joe's social stuff, all of that will be in the show notes for the episode. All of the Salesforce Admin episodes can be found at admin.salesforce.com. That is your one-stop for everything admin, including a transcript of this episode. Be sure to join our conversation in the Admin Trailblazer Group that is in the Trailblazer Community. Again, link is in the show notes. So until next week, we'll see you in the cloud.