ChatGPT agent mode: The “little helper” that transformed recruiting, crafted user personas, and solved parking nightmares | Michal Peled (Honeybook)

Michal Peled is a Technical Operations Engineer at HoneyBook who specializes in building internal tools and automations that eliminate friction for teams. In this episode, Michal demonstrates three practical AI use cases: using ChatGPT’s agent mode to automate LinkedIn recruiting, transforming customer research into interactive AI personas, and creating a custom calendar solution for a very San Francisco–specific problem—avoiding expensive parking during Giants games. What you’ll learn: How to use ChatGPT agent mode to automate LinkedIn recruiting and find high-quality candidates that manual searches missedThe step-by-step process for turning static customer research into interactive AI personas that product and marketing teams can actually useWhy NotebookLM excels at creating prompts from source material with proper citationsHow to structure agent-mode prompts to create effective “little helpers” that follow your exact workflowA practical framework for improving your prompts when AI tools aren’t giving you the results you wantHow internal tools teams can drive massive impact by focusing on eliminating friction in everyday workflows— Brought to you by: Brex https://brex.com/howiai—The intelligent finance platform built for founders Google Gemini https://ai.dev/—Your everyday AI assistant — In this episode, we cover: (00:00) Introduction to Michal and ChatGPT agent mode (02:10) Using agent mode for LinkedIn recruiting automation (05:14) Creating effective prompts for agent mode (10:50) Demo of agent mode searching LinkedIn profiles (16:29) Results and team reception of the recruiting automation (19:53) The outcome of implementing on Michal’s team (23:50) Creating custom GPT personas from customer research (28:43) Using NotebookLM to transform research into persona prompts (35:00) Adding guardrails to custom GPT personas (37:20) Demo of interacting with custom-persona GPTs (41:02) Creating a calendar automation for parking during baseball games (48:15) Lightning round and final thoughts — Tools referenced: • ChatGPT: https://chat.openai.com/ • NotebookLM: https://notebooklm.google.com/ • Claude: https://claude.ai/ — Other references: • Google Calendar: https://calendar.google.com/ • HoneyBook: https://www.honeybook.com/ • LinkedIn: https://www.linkedin.com/ — Where to find Michal Peled: LinkedIn: https://www.linkedin.com/in/michalpeled/ — Where to find Claire Vo: ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo — Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Claire Vo?

  We're going to start with something that we haven't actually seen on How I AI yet, which is agent mode in ChatGPT.

• 0:07Speaker 01

  My use case was with our hiring team. Part of their workflow is to browse through many LinkedIn profile and search for relevant candidates. It takes a lot of time.

• 0:19Claire Vo?

  Let's talk about the prompt. I'd love for you to go through how you thought about structuring it to make it effective with the agent.

• 0:25Speaker 01

  I want a little helper. I'm a recruiter. I want someone who is like me. So I started by telling it, you're an ID recruiter. And then I described what I wanted to do.

• 0:34Claire Vo?

  I love that you called it your little helper because don't we all want an AI little helper?

• 0:42Claire Vo?

  Welcome back to How I AI. I'm Clara, product leader and AI obsessive here on a mission to help you build better with these new tools. Today I have Mihal Piled from HoneyBook. Their technical operations engineer who's building tons of internal tools and automations to make their team's life easier and reduce friction. Mihal is going to show us some advanced features of ChatGPT, including agent mode, replicate not one, but five of their personas as AI identities, and save me a lot of time on my commute using ChatGPT. I'm really excited about this episode. Let's get to it. This episode is brought to you by Brex.

• 1:23Claire Vo?

  If you're listening to this show, you already know AI is changing how we work in real, practical ways. Brex is bringing that same power to finance. Brex is the intelligent finance platform built for founders. With autonomous agents running in the background, your finance stack basically runs itself. Cards are issues, expenses are filed, and fraud is stopped in real time without you having to think about it. Add Brex's banking solution with a high-yield treasury account, and you've got a system that helps you spend smarter, move faster, and scale with confidence. One in three startups in the US already runs on Brex. You can too at brex.com/HowIAI.

• 2:11Claire Vo?

  Mihal, thank you so much for joining How I AI. I'm excited to see what you have to share.

• 2:17Speaker 01

  Thank you so much for having me.

• 2:18Claire Vo?

  We're going to start with something that we haven't actually seen on How I AI yet, which is agent mode in ChatGPT. And so I'm wondering if you can just go ahead and dive into what was the problem that you were trying to solve? And why was this agent mode, this agentic browsing, the solution to the problem you're having?

• 2:41Speaker 01

  Our problem was, you know, same as our customers are having. You have to do your job. You have a job that you really love doing, and you have your professioncies and expertise. However, you spend a lot of your time doing the mundane, thoughtless, manual, repeating work in order to do, to get the information that you need. So my use case was with our hiring team. And as a recruiter, when you get a job description that you need to recruit,

• 3:19Speaker 01

  to find candidates for, part of their workflow is to browse through many lengthy profile and search for relevant candidates that may be relevant for the job descriptions. And it takes a lot of time, can be hours of browsing through profiles and going through all of the characteristics that they're looking for. So I wanted to take that load off of them. And ChatGPT agent mode came just in time. We all talk about what agent is and what agents do and how we can use them.

• 4:02Speaker 01

  In ChatGPT, it's very simple to understand. So you just open a chat with ChatGPT, but then you add an instruction and turn it into an agent mode, very simply, from the toolbar. And once it goes into agent mode, it means that it can take the prompt, or you can actually use specific prompts. To tell it not just to search for information online, but also to perform actions for you. And why did I need it in this case? Because I needed to log into LinkedIn. I don't want it to just search for profiles on LinkedIn,

• 4:44Speaker 01

  just just profiles that are publicly accessible. That's not the information that I need. So I needed it to log in into LinkedIn and I needed it to perform search and I needed it to go through the profiles and and look for the restrictions that I want to give it. And those restrictions were provided by the actual hiring team that they actually use it as requirements for potential candidates that they find.

• 5:15Claire Vo?

  Yeah, let's talk about the the prompt really quickly because I think this prompt is is interesting as I'm reading it. And I'd love for you to go through how you thought about structuring it to make it effective with the agent.

• 5:28Speaker 01

  Of course. So I usually start my prompts, begin my prompts with telling the GPT its role. And so here I told it, you are an IT recruiter. I want a little helper, right? I'm a recruiter. I want someone who is like me that will will assist me with my job. So I started by telling it, you're an IT recruiter. And then I described what I wanted to do, what the task is. Log into LinkedIn using my account. If not already logged in, let me take control and log in. It is something that is possible. Find up to five LinkedIn profiles where the current title and job description match the attached job description.

• 6:13Speaker 01

  And here is the part where I just uploaded a job description. In this case, it's for an engineering role. Okay.

• 6:24Speaker 01

  So I have the job description and I have the you are an IT recruiter. This is your job. This is the task and I provide like a full description of the task. Actually, actually describing what an actual IT recruiter would do. And then I added restrictions or special instructions. It doesn't matter, matter how you call them. But these are important because these give, don't just search for something that matches the description. Do it the way that we do it. And when our hiring team goes into a search,

• 7:03Speaker 01

  they have specific criteria that they go for. So I collected these and, and I added it as a list. As a restriction, I could call it instructions. It would, would have been the same. So candidates must be from Israel because the, the job is being filled up in Israel. Or currently working at an Israeli company. And they must be active in LinkedIn within the last three months because that's something that our hiring team is looking for. And the current job, job role must be close enough to the open role and entitlement and seniority.

• 7:44Speaker 01

  And also something that is special, the candidates must either work in their current workspace more than a year, or they can be unemployed, but no more than a year. And have worked in their last workplace for over a year. These are all things that I, I didn't invent them. They were taken specifically from our hiring process.

• 8:11Claire Vo?

  What I love about this is exactly what you said, which is, first, I love that you called it your little helper. Because don't we all want an AI little helper? That is, that is my goal. Maybe I'll rebrand my product to just little helper. But what I like about this is, you know, it, when you're building a, a tool like this or a prompt like this, the simplest way to get to a good outcome is simply interview somebody and say, Step by step, just tell me what you do, like, tell me what you do. And if you can codify what a person's step by step workflow is, and you can put that into a pretty simple prompt, which here it's only a paragraph and, you know,

• 8:51Claire Vo?

  three or four bullet points, you can replicate and automate that at scale. And typically, this is not the highest order of thinking you want your recruiter or sourcer to do. You don't want them just to build a list and be looking, is this person here a year or not? That is an input to what you hope is a great recruiting process, great outreach, all that kind of stuff. So, one, I think it's just really great to interview your colleagues and say, how do you do your job and what parts do you hate? And let me automate them. The second piece that I think is really interesting here is you're actually pretty specific about a couple outcomes. You're specific about the number of candidates that you want, so I think that's really helpful.

• 9:33Claire Vo?

  You're specific about a kind of threshold of matching your criteria. So you say 70%. And I often find these LLMs are very, you know, what is 70% matching? Like, it's not, it's not pure science, but they're pretty good at following a general threshold. So I think that is really interesting. And then the last piece I want to call out, which we'll maybe see in the demo, is agent, while it can be agentic and independent, can also be a co-pilot and collaborator. And so you actually instruct the agent when you're going to take over and when they're going to take over. And so I think that is also really interesting things for folks to know, is you don't just have to like press the button and walk away and let the agent run.

• 10:18Claire Vo?

  You can press the button and say, hey, wait, when you get to this point, let me take the next step. And then you can go on from there. So that's really interesting.

• 10:26Speaker 01

  Exactly. Or if you encounter a problem with this and that, stop and ask for my assistant. And that's exactly the agent, that's exactly the agent mode. Thinking about it as a little helper will really help you come up with good prompts for it.

• 10:47Claire Vo?

  Okay, I think you gave us our, our show title will be ChatGPT Agent Mode, Your Little Helper. So let's see how it runs.

• 10:55Speaker 01

  Exactly, exactly. So, once you start running it, and it's, this is something that is mind blowing for anyone who... Or tries it for the first time, even the ones who are, you know, very proficient with using AI tools. Suddenly you get like a computer, open it up in, in your, you know, you see, you, you see your, uh, your, your little helper actually doing things in the computer. So it's start, it started by reading my job description and then you can see it goes, it, it, it will try to go to LinkedIn, it will probably be already logged in because I logged in beforehand.

• 11:39Speaker 01

  And, uh, the thing I like the most, you see, is it's logged in. And then you can see like the arrow goes and clicks on things and searches on things and go through the list. And the thing I like the most is, is that during all of this time, you can see the thoughts of the agent. Now I will go to, uh, the feed page loaded again. I plan to click on, first I need to make sure, like you can see inside the brain of your agent while it is thinking. And so, uh, and all of this is live. So I will let it run here, but we can go and see, uh, results.

• 12:22Claire Vo?

  Yeah, you know, I, I want to call out a couple of things because I know that often on How AI, we have highly technical use cases for highly technical folks. But we also have a lot of people that are actually quite new to using generative AI tools and have probably been pretty familiar with ChatGPT and the direct experience. But I know if I showed my mom this, or, um, even some of my friends that maybe don't work in tech and said, hey, did you know that ChatGPT can open up a magic computer and navigate it and narrate its thoughts and look for things for you, they'd be pretty, pretty surprised. And I think, you know, as you watch this, what I hope our listeners and viewers are taking away is,

• 13:05Claire Vo?

  You don't just have to rely on text prompts in chats when you're using these tools. Now that the next kind of like evolution of these LLMs, especially the more like consumer-focused, general-purpose ones like ChatGPT have evolved, you actually have a lot more tools. And so I just want to call out some of those folks out there. I'm, you know, I'm thinking a little bit of my parents and some people in an older generation who are like, how do I get from here to here? I need help, you know, searching for flights or I need to do a certain kind of research on a niche site. Having sort of this expert computer operator on hand, I actually think is going to make

• 13:49Claire Vo?

  information more accessible to folks, but it's also going to make UX and websites more accessible to folks that don't have the time to figure out, how do I use the best filters on LinkedIn or those sorts of things? And so I just, I want to make sure that people that have not experienced agent mode, and I know we're all on the edge, so maybe all of us have, just, you know, take a minute to appreciate the kind of use cases that this opens up. Also, it's just fascinating to watch.

• 14:17Speaker 01

  Yeah.

• 14:18Claire Vo?

  AI operators.

• 14:20Speaker 01

  Of course, first time I tried it, I just sat and watched the thoughts of the agent while it was thinking.

• 14:28Claire Vo?

  Going to our more technical audience, though, a couple of things that I want to call out is, one, props to the OpenAI ChatGPT team. What a great user experience design here. Like, it could feel very strange to watch an agent browse a website. It could either be boring or weird. And I think this user experience of like being able to see where the cursor is, showing the reasoning and thoughts, watching it navigate is actually pretty entertaining. That's a hard thing to pull off for a consumer product. And so for anybody designing AI products, it's worth thinking about some of these interaction patterns here. And then again. I just think about how long this would take someone to do.

• 15:12Claire Vo?

  We're watching it because I'm trying to narrate some of the features, but you know, you could, you could walk away. You could go to a meeting while this happens, or you could do something, something else.

• 15:23Speaker 01

  If you have chat GPT on your phone, you will get notification and notification when it's done to tell you that it's done. And, and here are the results for you, where you said little helper.

• 15:35Claire Vo?

  And the last thing I'll call out, I love, I really do love this use case is I do this specific thing all the time. As a hiring manager, executive leader in an organization, I was constantly looking for like, who's a senior director of DevOps and platform infra, who is either in San Francisco or works for a San Francisco based company, who has experience in dev tools that, you know, one, one change I would maybe make on your prompt is like, is one or two connections away. So I can actually message them or get a back channel reference on that. I did this all the time. I had my hiring managers do this all the time.

• 16:17Claire Vo?

  So even if you're not in recruiting and you're just somebody who does hiring, I think this specific workflow is really, really useful.

• 16:24Speaker 01

  Yeah, definitely. Uh, that's an excellent use case that you, you just mentioned.

• 16:29Claire Vo?

  Well, let's actually, um, let's look at the output. We'll, we'll let this run, but I know you have an example output for us.

• 16:36Speaker 01

  Yeah, it runs. I have an output that actually, uh, worked for 10 minutes, just that. And within these 10 minutes, I got a list of five candidates as I requested for. And you can see the match score. Well, having a match score or rank for a result is something that I really love doing. It's not a must, but if you give a specific, if you provide specific requirements and ask for a match score, it is easier to understand what the results are more, have more quality for you. I mean, otherwise you could just get a table of like, these are the five results.

• 17:21Speaker 01

  But is someone of them better or maybe a better match for what I need than the others? I won't be able to see it unless I instruct the, the GPT to provide me with some score.

• 17:38Speaker 01

  So it's not an exact science, but it does give you some kind of a way to compare between the results. So I will say someone who got 90% match is probably as, as like probably will be a better match than the 78% match. And I will have to go deeper and understand why.

• 18:03Claire Vo?

  Yeah, one, I'll call out a couple of things here that I think are for interesting for people to look like. I know we were talking before the show, you actually made this anonymized data, just so we weren't showing people's profiles or, you know, showing how person A versus person B fit a specific job you're hiring for. But I will say anonymizing candidate profiles is actually a pretty standard practice in a lot of recruiting flows, just to make sure you're not biased, this school, that school, this person, that person, this name, that name. And so I actually kind of like this flow where you're really just comparing the qualifications against your stated objections or objectives. And so I think that is a really

• 18:46Claire Vo?

  interesting kind of meta flow that you're showing here. The second thing that I wanted to say as I was reflecting back on agent mode is it's almost exactly like a recruiter or sourcer would navigate LinkedIn, except for one thing. When I log into LinkedIn, I don't go straight to the job to be done. I don't go straight to that search bar and search for like VPs of engineering. No, no, I get distracted by the, by the notification. I start reading the feed. I'm responding to comments. I go through my inbox. And so I think like, why is it 10 minutes? It's 10 minutes because it's like pretty hyper, hyper focused and efficient, but it's also 10 minutes because you're not getting so distracted

• 19:28Claire Vo?

  with all the other things in, in the application. And you can really just get the agent to focus on the task, task at hand. So maybe it's a way for us to all break. Sorry, LinkedIn, LinkedIn growth PMs, I apologize, but it's a good way for us to still get the value of these platforms without getting our time sucked into the less value generating aspects of them, maybe.

• 19:53Speaker 01

  Yeah, that is correct.

• 19:55Claire Vo?

  So tell me a little bit about how this was received by the team. I'd love to know the kind of outcomes here.

• 20:00Speaker 01

  Yeah, well. I I I will be real and say that um like the first result that I got, I was very skeptic about. So I just took the the table and I sent it to our hiring manager. And I told her, this is the job description. This is what AI found for me uh in LinkedIn. If you can go through their results and let me give me feedback. Are there good results? Are we familiar with these candidates? Did we try to reach out to them? Or uh you're looking at them and say, oh, no, that's a terrible fit. I don't know why, why, why this person is even in this table.

• 20:43Speaker 01

  Um. And so she went over or over them. You can see that the table has link to the direct, like the the LinkedIn profile per candidate. So she scanned those five profile. And she came back to me and she said, well, uh, you know what? Out of these five, four of them were never found by us manually and they really fit the description. So we would wanna approach and and, you know, try, try to get them to uh to come for an interview. And the fifth one was actually one that we caught manually and is already coming for an in an interview.

• 21:25Speaker 01

  Uh. And so to me, it was a great sign for quality. I mean, it it's not just a list of names. Those are actual, real quality candidates that we can work with. And so now, now they want, they want the agent to run on a lot more uh job description, many more job descriptions that we have. Provide them with more than five candidates. I wanted just five to see if if it if it's worth something. Um, yeah, but now it's going to be a real part of of their hiring process, freeing their their time to do other things that they love and appreciate a lot more.

• 22:10Claire Vo?

  Yeah, and I can't emphasize what you're saying enough because so many people push back on AI, saying, yeah, you may get speed and you may get efficiency, but you're not getting quality. And my experience has has been the opposite of that. You get speed and you get quality. And again, it's those it's that last mile, those edge cases, those ones that are like just a little hard to find, a little hard to research, where I think AI can increase the quality of that of that last bit. And so it was it's amazing to see that this work for your recruiting has given me so many ideas, not, you know, not just recruiting use cases, but just in general, one, people finding use cases. I was thinking about how you could find great candidates

• 22:51Claire Vo?

  or customers on like X or LinkedIn. And then the other thing that I think is is really great here is just showing we don't get a lot of GNA functions. We don't get a lot of people functions getting love in how AI I feel like all the noise is about like product design, engineering, support. And so I just love seeing the recruiters get some love here because you're the people that bring in great talent and fun colleagues to work with. So thank you for showing this.

• 23:20Speaker 02

  This podcast is supported by Google. Hey, everyone. Shreeta here from Google DeepMind. The Gemini 2.5 family of models is now generally available. 2.5 Pro, our most advanced model, is great for reasoning over complex tasks. 2.5 Flash finds the sweet spot between performance and price. And 2.5 Flashlight is ideal for low latency, high volume tasks. Start building in Google AI Studio at ai.dev.

• 23:50Claire Vo?

  Let's zip to your second use case, which I think is really, we're going from finding real people to creating fake people. So I'm excited about this next workflow.

• 24:02Speaker 01

  That's an excellent description of it. So let me ask you that. Imagine you're a business owner and imagine being able to talk to thousands of your potential customers all at once and gather their insights on your planned ad campaigns, planned features, product experience, all from your phone or tablet 24 hour a day with one click of a button. Actually talk to, actually talk to them. I thought it's mind blowing. And so it started with HoneyBook invested in comprehensive customer research with a third-party provider. We interviewed hundreds

• 24:47Speaker 01

  of our target small business owners and they created five detailed buyer personas. But the research was trapped in documents, hundreds of pages of insights that teams rarely referenced because it was too time consuming to extract actionable information when making product or marketing decisions. So the end goal was, we have five personas, we want to talk to them, let's create a chat GPT that is that person, that actual person. And so I started with, and here that there are some technical takeaways, but here I want to put the spotlight on the

• 25:32Speaker 01

  thinking process. Because it's very easy to go to chat GPT and everyone with a subscription tier of, it's not a plus, a plus subscription tier and above can create their own custom GPT. And so you go to create a custom chat GPT. It's quite, it's a quite simple process.

• 25:59Speaker 01

  You add a name to your GPT, a description, but the most important parts are the instructions you're providing it with and the files that you can upload as a knowledge for that chat that you're talking to. So I needed five like them. But first I thought, okay, this is all I know about custom chat GPTs. I can basically take all of the documentation from the interview and just upload all of the files, text files, presentations, whatever, into this custom chat bot, provided with some instructions on how to answer, what the research was about, what to say, what not to say, and ask it questions about the research itself.

• 26:43Speaker 01

  But that's not what I wanted. So I was like, okay, if I'm taking just the files per persona, so I'll concentrate in one persona, take the files related to that persona, upload it to the chat, instruct the chat what that persona is, how to read the files, what's included in the files, then I'll be able to maybe ask about that persona. And I will probably get answers like, that persona would have done this, or that persona would prefer that. But it's not like talking to the persona. I'm still talking about the persona and not with it.

• 27:27Speaker 01

  And so I realized I'm not going to rely on uploaded files for the chat GPT. I need the instructions to be the main and most important part of what consists of that persona. And the instructions here will not be what's in a file or talking about someone else. There will be exact instructions that goes, that go like, you are that person, and this is your belief system, and this is how you run your business, and this is how you deal with media, and this is how you deal with technology. And everything has to be super, super, super tight.

• 28:12Speaker 01

  So that chat GPT wants run in live will actually become that persona that can answer based on what it knows about itself, not files that are attached to it.

• 28:27Speaker 01

  And so I needed to bridge that gap. I have all of the research there. I need to make a person out of it, or five, five of them, actually.

• 28:39Claire Vo?

  Okay, so you heard it here first. This is our first HowAI where we are manufacturing not one, not two, not three, not four, but five people. So show us the process.

• 28:51Speaker 01

  Yeah, so I thought about it and then I decided to go to another tool that I really like. This is Notebook LM. It's a Google's tool. And Notebook LM, the thing I like about it the most and the reason I picked that tool in order to construct the instructions or the prompt per persona is actually there are several reasons. But one of them is Notebook LM allows you to upload your own sources and can answer only based on these sources and not things that it goes and finds online or thinks or knows or filling in the gap. This is the information.

• 29:37Speaker 01

  You ask me about something, I will answer based on the knowledge that you provided alone. Also, it allows you to check and uncheck the sources that you want to rely on. So I can ask a question without relying on the buyer journeys, for example. And then the answer will not include that that part of the knowledge, things that I cannot do in chatgukity or anything else.

• 30:04Speaker 01

  And then there's this chat part within the notebook where it's Gemini based. Gemini is Google chat model, okay? And in this chat window, I prompted the chat.

• 30:23Speaker 01

  Again, you are an expert prompt engineer, again with the role, what you are. Specializing in creating custom GPTs by providing strong AI prompts. And then the mission, what your task or mission is. Uh, your mission is to create AI prompts for custom GPTs representing entrepreneurs and small business owners. Who are the decision makers, and so on. So you will craft highly detailed, nuanced, and authentic chat GPT prompts for five distinct buyer personas based on your sources. I never told it what were the personas. It had to get it from the sources.

• 31:05Speaker 01

  And that's uh, the, the most important part again is guidelines. I mean, prompts are nice. It, it usually, they usually should come with some guidelines, instructions. Um, anything that you want to be, to, to, uh, the chat to take specific care of. So in my case, the guidelines were, uh, to ensure that the prompt correctly and fully described the core identity, mindset, decision-making style. I didn't want the chat to decide on itself. What, what I care for about those personas, because I knew what I care for.

• 31:47Speaker 01

  So I wanted their mindset and decision-making style and tone and communication style. And then, um, the business needs and the technology stack. And the journey map, social media preferences. I, I pointed the chat to exactly what I needed to get out of this research. And then that's another important one. I think one should not go on without that instruction. Don't add or modify text that is not written or implied in the text. I know you're creating, I'm turning you down. The text to describe a specific persona must remain true to the original persona.

• 32:29Claire Vo?

  Yeah. I'm laughing because yesterday I literally wrote a prompt that was like, do not make up any links. I had a thing that was making up, do not make any up any links that are not in your source of links. Like, and it's so funny, we get so used to operating these chatbots as if they have human reasoning. And sometimes they have kind of like superhuman reasoning. And sometimes they just do stuff that a human would never do, like just make up something. And so I think this third prompt, we'll zoom in on it on the show, is probably applicable to a lot of things, especially when you're trying to constrain an LLM space to a specific set of data and inputs.

• 33:14Claire Vo?

  So it's a good prompt, everybody should use the don't make up stuff prompt. Your hallucination rate will drop.

• 33:20Speaker 01

  Yeah.

• 33:22Speaker 01

  Yeah, exactly. Wow, it is very, it is crucial to add those things and to think about them.

• 33:30Claire Vo?

  Yep.

• 33:31Speaker 01

  Yeah. Um, so the result was, and another thing that Notebook LM is good at doing is you can save the responses of the chat as notes and those notes are saved here for you to look at later. So I can show you an example of the notes that it created, but mainly I just took the prompts. I went over them. The important thing about the prompts is that's another strength of using Notebook LM. It uses, um, it uses citations.

• 34:14Speaker 01

  So you can actually go over, um, a piece of information that the chat decided this persona has and see where did he take it from.

• 34:26Speaker 01

  And and just make sure and verify that it went through all of your uh data information and didn't invent anything.

• 34:35Claire Vo?

  I'm gonna laugh because I'm from Austin and I'm pretty sure I know people pleaser, whatever, Parker. Um, so it's like a very accurate Austin entrepreneur persona. If folks are wondering if this is creating high quality, high quality Robs.

• 34:52Speaker 01

  Yeah, yeah, yeah.

• 34:55Speaker 01

  So eventually, yeah, I, I, what I did is just, I took the prompts. I did need to refine them a little, okay? Because um, even with all of my instructions, Gemini didn't exactly realize what kind of prompt it needs to create. So it was missing some guardrails. It was a little too long. Uh, the chat G P, the custom G P T uh instructions are limited to eight thousand characters and it created some of the prompts uh being longer than that. So I did need to deal, to do a little refine and create uh stronger prompts.

• 35:37Speaker 01

  So for example, and I'll show you in the demo, I needed to add, I used chat G P K itself or sometimes Claude because I like working with Claude. Um, I use them just to uh tighten the, the instructions a little and make it more robust and add guardrails. So I added, for example, um, you do not act as a general person, per, purpose assistant. You do not ask follow up questions. You avoid slang, bad language, or this, distasteful content and keep communication respectful and inspiring. You avoid political, religious, gender, or racial commentary.

• 36:21Speaker 01

  And I really wanted to add it, that's another key point for creating custom G P Ts that need to talk as a person because believe me.

• 36:33Speaker 01

  Those people work with you, they are your friends. The first thing they will try with a chat GPT-like persona is to tackle them with swear words or their their ideas about political things or, I don't know.

• 36:51Claire Vo?

  I was gonna say.

• 36:52Speaker 01

  For food, so.

• 36:55Claire Vo?

  This, this maybe should be a default prompt wrapper on all enterprise GPTs and it would save us all a lot of, a lot of heartache.

• 37:05Speaker 01

  Yeah, so you can see it, it's in order of what I asked for. So core identity, mindset, business needs, technologies, tech, whatever. And then what you get is then it's the time to actually test them. So we created those five and I can go to Balance Blake. You can see she's one of the most talked to internal chats. So we can go to Balance Blake and I can ask her, what kind of ad headline would catch your attention?

• 37:49Speaker 01

  Maybe I'll move it. Would catch your attention during a busy workday? Don't you? What if you wanna know the, that thing about your ideal or prospect client? And I can, I can send her the question. And then from scanning quickly between meetings or juggling, a few would catch my eye. Save 10 hours a week with this tool, no tech skills needed. Or from key, from chaos to clarity, one dashboard to run it all. Your clients don't need another email, they need this.

• 38:32Speaker 01

  And this persona actually explains why, even why every one of these headlines will catch their attention. And I can take the same thing and try it on a completely different persona like Aiden and Aiden will give me a completely different answer. Aiden will say, I need.

• 39:01Speaker 01

  One that respects my time and speaks directly to the pain I'm feeling in that moment. Still doing admin during edit days, ears are to reclaim five hours a week. Other variations that might grade me, win better clients without burning out and so on and so on. So each persona actually answers based on the persona that we got from research. And that single persona represents thousands of potential customers. And so you can try headlines or you can try a product journey. What would be your, your best first impression when you get into a new CRM?

• 39:48Speaker 01

  What would be the feature that will convince you not to churn a CRM? So you can try it on them. They are 24/7 ready to talk to you on whatever. And I really like them. I mean, personalizing those personas has changed the way we work with them.

• 40:09Claire Vo?

  I just love this workflow and to recap it for folks, you took a bunch of, I'm presuming, pretty expensive research. That probably sat in a bunch of PDFs and docs where, you know, we occasionally said head down Hayden, but otherwise did not use these personas. You use notebook LLM to create a prompt that embodied the personality of the persona. You put those personas in GPTs and now you can see that dozens of times your colleagues have gone to them to brainstorm with the persona, which I think is really interesting and it's giving me a lot of ideas. So many people go to just plain chat GPT. It's like, give me five headlines for an ad campaign as opposed to going and sitting with, you know, sitting with your fake persona and saying, what, what, what ad campaigns would work on you?

• 40:54Claire Vo?

  So I love this flow. We learned a little bit about the strengths of notebook, LLM, GPTs and flipping these like sort of personas on their head. Let's go to workflow three, which I will tell you, I personally, I have a personal connection to. So people in San Francisco, listen, here's the use case for you. Let's jump to your last use case and then we can get you out of here.

• 41:19Speaker 01

  Well, this one is actually, yeah, a really big pain.

• 41:23Claire Vo?

  And so, yeah.

• 41:27Speaker 01

  Favorite your soul.

• 41:30Speaker 01

  Well, imagine getting ready in the morning, driving to work, already planning it for your busy schedule and morning routine, only to discover that parking in your favorite parking, in your favorite parking lot now costs forty dollars an hour instead of the usual fifty dollars for the entire day that you paid so far. So this can ruin your entire day for sure. So the thing is, Annie Book's office is right next to Oracle Park, where the San Francisco Giants play. And on game days, especially those taking place in the morning or afternoon, parking rates spike from fifty dollars a day

• 42:15Speaker 01

  to forty plus dollar per hour. Our team was constantly getting caught off guard, showing up to expensive parking or scrambling to find remote cheaper alternatives. We needed a way to know in advance when to take public public transit instead of driving to work. And so the solution was, I was thinking, okay, I think let's share a calendar, like a joint calendar that just show you on which days parking lot prices are likely to surge. I needed two things for that. I needed to figure out when games are taking place in the ballpark,

• 43:00Speaker 01

  and I needed to create a calendar file. I had no idea how to do. Calendar file is an ICS file. This is the type. I have no idea how to create one. Okay, whatever. Let's go to ChatGPT.

• 43:14Claire Vo?

  So while you're getting this up, I am just smiling and laughing because my Launch Darkly office was right behind Oracle Park. And I got there, I found a twenty dollar a day parking. And I still have, like, I texted my friend the day I had to pay like a hundred dollars.

• 43:31Speaker 01

  Yeah.

• 43:32Claire Vo?

  To park. I was already down there, ready for a meeting. And so San Francisco downtown is, we're coming back, people. But don't forget that the summer, the summer baseball season, and sometimes they have two games a day. They have double headers.

• 43:47Speaker 01

  Yeah, yeah, yeah. That is correct. And then you have, yeah, walk, walk over there. Just don't use your car.

• 43:55Claire Vo?

  Don't go, just don't go.

• 43:58Speaker 01

  If you can avoid it, avoid it. Um, yeah, so I was like, let's try chat GPT. I mean, this should be a simple one, hopefully. So I tried a naive one. Okay, as you can see, this prompt doesn't tell the chat you are this or that. I was like, I have a simple question. Fine, uh, all home games that take place in Rockwell Park in San Francisco during the next six months. I use six months because I knew it's uh, the end of the season coming soon. So you can ask for the next year, whatever. Filter out only the games that start anywhere between morning to 2 P M.

• 44:36Speaker 01

  Because if uh, games are taking place in the evening, when we arrive in the morning, the, the prices are still the usual sane one. Uh, so using these dates, create an I C S, I C S file for Google Calendar. That's the calendar that we're using at work. Uh, that will show these dates as an all day event. I wanted, I wanted just to see very clearly uh, potential dates, days in my week where I rather avoid driving uh, to the office. And a key point was availability free.

• 45:15Speaker 01

  Otherwise, this all day event will just uh, block my entire day, show me as busy, just because the Giants are playing. Uh, also, the event description should contain the game details and time. I wanted to add that so I can verify that the game is, is the one that I'm thinking about, that it's actually one that is taking place there. I, I like to add those extra verification point, validation point, just to make sure that, that uh, we know what we're talking about. And then I also added an instruction other than just output the ICS file that I need, the calendar file.

• 46:00Speaker 01

  I want a textual list of all the dates, times and events included in the created calendar. Now, basically, if it was human, they may have been a little, you know, offended by me. Why don't you trust me? But but Chantilly doesn't care. So it thought for 36 seconds, provided me with the file and also with a list of all the remaining games, because the season is about to end. All the remaining games that are taking place in Arakal Park with their dates and times. And so I know all of these are included in this file.

• 46:38Speaker 01

  I just took the file, I installed it or added it to my personal calendar or work calendar. I also shared it with all of my team members. And then you upload it and then you can see, for example, that on September 10th, there's a game, Arizona Diamondbacks are playing the Giants. At first pitch is 12:45. So better avoid driving to work that day.

• 47:11Claire Vo?

  I I love this so much because again, I have hit this problem so many times and you don't want a calendar that has the game in the middle of your work day, right? You want to customize. You probably could have filed like an SF Giants schedule calendar. That's not exactly what you wanted and it would have had all these games, weekend games, night games, all these things.

• 47:35Speaker 01

  Away games as well.

• 47:36Claire Vo?

  Away games. Exactly. So you can have this really filtered to what you want. I'm going to give you one, one improvement that you can make to this.

• 47:45Speaker 01

  Yeah.

• 47:46Claire Vo?

  Which is for the night games, you should put an alert because if you park in the morning. And you're still there for the night game? You should just go to the game. It's a great, it's a great stadium.

• 47:57Speaker 01

  That's an excellent suggestion.

• 47:59Claire Vo?

  To watch the games, good view. It's finally warm in San Francisco, so it won't be freezing.

• 48:04Speaker 01

  Yeah, and you parked cheap.

• 48:06Claire Vo?

  And you parked cheap. I've done that once or twice where I parked. I'm like, I'm not leaving, honestly. I don't want to deal with the traffic. I'm just gonna go, go to the game. This is a great little workflow. I think like a very good little helper, personal workflow that helped you and also your team. So thanks for sharing. So just again, to recap your use cases. First one we did, oh, agents for recruiting, loved it. So straightforward. I'm going to use that right away. Two, generated persona GPTs. And three, make your daily life a little bit easier by giving you ambient information that can help with your commute. So we're going to wrap our episode with a couple lightning round questions and then get you out of here.

• 48:49Claire Vo?

  The first one I have to say is you are the little helper. You seem to be all over HoneyBook, just helping recruiting, helping the product team, helping the whole team. You know, tell us a little bit about your role and what you think this role will look like. Do people need a dedicated person or a dedicated team towards these automations? What do you think the future of this inside companies is going to look like?

• 49:16Speaker 01

  Okay, for sure. Well, I love nothing more than talking about myself. So my title is Technical Operations Engineer, but it encapsulate a lot of other things. So I do, I research and integrate paid tools, but a lot of the times you don't find the exact paid tool that you want. So I build them. I build internal tools and processes. I'm using no code solutions, automations, and also coded solutions. It can be an AI-powered Slack bot. It can be an internal application.

• 49:57Speaker 01

  It could be integrations between two different applications that don't speak with one another. So I come in the middle and I connect them.

• 50:08Speaker 01

  It's not just doing things for others. It's also teaching and enabling others to do for themselves. I'm a great believer in enabling. So I do company-wide presentations, I do personal advisory, training classes, documentation. Actually, um, Asani Book is a, is a platform for small businesses, okay? I see each team and department within Asani Book as a small business of its own. They provide services, they collaborate with other teams, other businesses. They have their own goals, they have their own expertise, passion for different things.

• 50:53Speaker 01

  And they all want to spend less time on manual, thoughtless, repetitive tasks. And more time doing what they love. So this is where I'm coming for. This is what I'm trying to do. This is what I'm trying to provide. To take the, to take the, the, the friction away and leave you to do what you love.

• 51:17Claire Vo?

  One thing I want to call out for folks is I've been in tech a long time. And unfortunately, basically up until the last couple of years, I feel like internal tools teams were very starved for resources and occasionally starved for respect. It was like, oh, you got the product teams and they're customer-facing and they build all the cool products. And like, internal teams are always underfunded, not enough people, blah, blah, blah, blah, blah. And I think now, what I love is this is the moment for internal tools teams to shine, to do legitimate, great, high-impact product work. I would recommend anybody who really wants to lean into AI, find their way into this kind of role.

• 51:58Claire Vo?

  Because honestly, a lot of times it's moving faster than you can even get some of these AI experiences into product, which have. A lot of like customer impact and legal implications and blah, blah, blah. But if it's, if it's all internal tooling, you can kind of let it rip. And so I just want to like shout out to all the internal tools teams out there that I know to date have not got the love and respect that they deserve. This is your moment. You can have really high impact and do some pretty great work and honestly do a lot to differentiate your career in, in this moment by taking advantage of the fact that you can build these tools. So I think you are a great model and I'm excited to see you do it.

• 52:36Speaker 01

  Yeah.

• 52:36Claire Vo?

  Okay. Last question. You're a very good prompter. In fact, you create prompters to create prompts.

• 52:42Speaker 01

  You want to.

• 52:43Claire Vo?

  But when AI is not replying to you the way you want, when it is frustrating, when the agent gets distracted by the notifications in its inbox, what is your prompting technique? Are you, all caps, do you yell?

• 53:00Speaker 01

  You do. Wow. Well, I, I love using all caps and no one can persuade me otherwise. I mean, there will be people saying it's just a robot. It doesn't care if it caps or not, but I'm like, no, it takes me a lot more seriously when it's all caps. Um, but, but I will say, um, my go-to technique would be to take my current prompt and then tackle the chat GPT with my prompt, asking it to make it better. And how do I do that? It's not just, this is not working, make it better.

• 53:44Speaker 01

  Even as a person, I, I would, I have no idea what you want from me. Um, so I, I'm just going with, this is the prompt I'm using. This is, this is what's wrong with the output. Like I outlined, the output is inconsistent, uh, contains too many hallucinations, invent things that are not there. That's the second part. And then I, uh, it's very important for me that the prompt will one, two, three, four, I, I list the things that not just what, what is wrong,

• 54:24Speaker 01

  but while I want it to be right. And then I also add, um, I also add it, I give it permission, take away everything that doesn't work well.

• 54:37Claire Vo?

  Yeah.

• 54:37Speaker 01

  You can delete things from my prompt, you can rewrite things that don't work well, and you can add things that you feel are, will do a better job. And I feel like given permission to change, delete, remove, whatever, uh, provides a better output because otherwise, and ChatGPTs tend to be pleasers. They will may try to, uh, use your prompt and not move a lot out of it. Like this is yours. This is so great. I'm not going to change it. No, I allow you to change it. I allow you to rewrite it completely. And I tried it several times on several prompts, not just my own.

• 55:20Speaker 01

  People are coming with me with, why does my custom ChatGPT act so badly? Um, now like, let's, let's take your prompt and rewrite it using ChatGPT. So I go with that template and, and like first try, it's amazing. First try, you get a, a prompt that is much, much, much better. And usually it's all, it only takes that one iteration for it to work exactly as you wanted it to. Um, so that's my tip.

• 55:52Claire Vo?

  I, I love it. It's a very professional tip, um, that I will use in my moments where instead I just want to write no in all caps, uh, which, you know, I try to pretend that I'm this very, you know, patient and sophisticated and AI friendly prompter, but I think the more comfortable I get with it, the more ridiculous my prompts get. So it's a good reminder that structure can help. Well, this has been so fun. Where can we find you and how can we be helpful to you?

• 56:20Speaker 01

  Uh, you can find me in LinkedIn. Uh. I am linkedin.com/michael.paled

• 56:31Speaker 01

  And I work at HoneyBook, so you can just search for Michael Paled HoneyBook and find me. I would really love to connect with anyone who is into automation, AI, new things, whatever. I want to see what you do. I want to see what you're working on. I get constant ideas from other people in LinkedIn, in Facebook, whatever.

• 56:58Speaker 01

  I'm there. And from you, you saw something that I did here, and it's struck you with a great idea, a way to improve it. You want to suggest things that I can do better. Or even if you want more information from me, just feel free to reach out, ask questions. I'll be happy to answer. It's one of my favorite things to talk about my work. Feel free to do that.

• 57:34Claire Vo?

  Well, you heard it. Drop questions in the comments, connect on LinkedIn. And if HoneyBook is hiring, you now know how they search for great candidates. So if you're a great candidate.

• 57:45Speaker 01

  Yeah, we are hiring. Make sure your profile is well structured, well made.

• 57:56Claire Vo?

  You know, maybe use the agent to say, I'm applying for this job. Could you find me on LinkedIn as a good match? And what would I do to improve it? That's the last tip for How AI, professional AI girl right here. Well, it was so nice to have you. Thank you so much for showing us our workflows. They're really inspiring and we will see you soon. Thanks.

• 58:15Speaker 01

  Thank you so much.

• 58:17Claire Vo?

  Thanks so much for watching. If you enjoyed this show, please like and subscribe here on YouTube, or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time.