ChatGPT agent mode: The “little helper” that transformed recruiting, crafted user personas, and solved parking nightmares | Michal Peled (Honeybook)
Episode
58 min
Read time
2 min
Topics
Career Growth, Artificial Intelligence, Software Development
AI-Generated Summary
Key Takeaways
- ✓Agent Mode Recruiting: ChatGPT agent mode logs into LinkedIn, searches profiles using specific criteria (Israel-based, active within three months, one year minimum tenure), and delivers five qualified candidates in ten minutes—four were new discoveries the hiring team hadn't found manually, one was already interviewing.
- ✓Persona Creation Pipeline: Upload customer research files to NotebookLM, prompt it to generate detailed persona instructions with citations, refine output to under 8,000 characters, then deploy as custom GPTs. This transforms hundreds of pages of unused research into conversational personas teams actually consult dozens of times.
- ✓Prompt Engineering Framework: Start with role definition (you are an IT recruiter), add task description, include specific restrictions as bullet points, and always add guardrails like "don't add or modify text not written or implied in sources" to reduce hallucinations and maintain accuracy in outputs.
- ✓Prompt Debugging Technique: When outputs fail, feed the broken prompt back to ChatGPT with three components: what's wrong with current output, numbered list of desired improvements, and explicit permission to delete, rewrite, or add anything. This typically fixes issues in one iteration without manual rewriting.
What It Covers
Michal Peled from HoneyBook demonstrates three ChatGPT workflows: using agent mode to automate LinkedIn recruiting searches, converting customer research into interactive AI personas, and creating customized calendars to avoid parking price surges near Oracle Park.
Key Questions Answered
- •Agent Mode Recruiting: ChatGPT agent mode logs into LinkedIn, searches profiles using specific criteria (Israel-based, active within three months, one year minimum tenure), and delivers five qualified candidates in ten minutes—four were new discoveries the hiring team hadn't found manually, one was already interviewing.
- •Persona Creation Pipeline: Upload customer research files to NotebookLM, prompt it to generate detailed persona instructions with citations, refine output to under 8,000 characters, then deploy as custom GPTs. This transforms hundreds of pages of unused research into conversational personas teams actually consult dozens of times.
- •Prompt Engineering Framework: Start with role definition (you are an IT recruiter), add task description, include specific restrictions as bullet points, and always add guardrails like "don't add or modify text not written or implied in sources" to reduce hallucinations and maintain accuracy in outputs.
- •Prompt Debugging Technique: When outputs fail, feed the broken prompt back to ChatGPT with three components: what's wrong with current output, numbered list of desired improvements, and explicit permission to delete, rewrite, or add anything. This typically fixes issues in one iteration without manual rewriting.
Notable Moment
The recruiting agent found four qualified candidates the hiring team had never discovered through manual searches, plus identified one candidate already scheduled for interviews—validating that AI-powered sourcing delivers both speed and quality improvements over traditional LinkedIn browsing methods.
Episode Transcript
Gonna start with something that we haven't actually seen on How I AI yet, which is agent mode in ChatGPT. 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. 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. I want a little helper. I'm a recruiter. I want someone who is like me. So I started by telling you if you're an IT recruiter, and then I described what I wanted to do. I love that you called it your little helper because don't we all want an AI little helper? Welcome back to How I AI. I'm Clara Veaux, product leader and AI obsessive here on a mission to help you build better with these new tools. Today, I have Michal Paled 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. Michal's gonna 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. If you're listening to the 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. Michal, thank you so much for joining How IAI. I'm excited to see what you have to share. Thank you so much for having me. We're gonna start with something that we haven't actually seen on HowIAI yet, which is agent mode in ChattGPT. 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? Our problem was, you know, same as 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 profesiencies and, and expertise. However, you spend a lot of your time doing the the, mundane thoughtless, manual repeating work in order to do, to get the information that you need. So my use case was with our …
Get the full transcript (8,914 words) + summary by email — free
One-time email with the complete transcript and AI summary of this episode. No account needed.
One email, no spam. We’ll also show you what SignalCast does.
You just read a 3-minute summary of a 55-minute episode.
Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from How I AI
Build your own company brain: the enterprise AI playbook from Stripe’s engineering team | Sharadh Krishnamurthy
Sep 7 · 50 min
This Week in Startups
How These 3 Founders are building on Open Claw | E2248
Feb 12
More from How I AI
GPT-6 Astra is a banger - here’s everything I’ve built
Sep 3 · 32 min
The Startup Ideas Podcast
Inside $180B Co-Founder's AI Agent System
Jan 26
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links.
Tools
by Google
“Upload customer research files to NotebookLM, prompt it to generate detailed persona instructions with citations, refine output to under 8,000 characters, then deploy as custom GPTs.”
by OpenAI
“Michal Peled from HoneyBook demonstrates three ChatGPT workflows: using agent mode to automate LinkedIn recruiting searches, converting customer research into interactive AI personas, and creating customized calendars to avoid parking price surges near Oracle Park.”
by LinkedIn
“ChatGPT agent mode logs into LinkedIn, searches profiles using specific criteria (Israel-based, active within three months, one year minimum tenure), and delivers five qualified candidates in ten minutes.”
company
“Michal Peled from HoneyBook demonstrates three ChatGPT workflows: using agent mode to automate LinkedIn recruiting searches, converting customer research into interactive AI personas, and creating customized calendars to avoid parking price surges near Oracle Park.”
More from How I AI
We summarize every new episode. Want them in your inbox?
Build your own company brain: the enterprise AI playbook from Stripe’s engineering team | Sharadh Krishnamurthy
GPT-6 Astra is a banger - here’s everything I’ve built
Grok Bot vs. OpenClaw: How I replaced my entire agent stack
How I turned Claude into a self-improving PM assistant | Daniel Blum (PM, Melio)
I spent $20,000 on Devin in a month. Here’s what I learned | Ryan Carson (solo founder)
Similar Episodes
Related episodes from other podcasts
This Week in Startups
Feb 12
How These 3 Founders are building on Open Claw | E2248
The Startup Ideas Podcast
Jan 26
Inside $180B Co-Founder's AI Agent System
Lenny's Podcast
Aug 30
AI’s third era: the rise of persistent AI coworkers | Tara Seshan (OpenAI’s product lead)
The Vergecast
Jun 5
This is your laptop... on AI
The Startup Ideas Podcast
Mar 26
I Built an AI Agent Company (From Scratch)
Explore Related Topics
This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's AI & Machine Learning Podcast Insights — cross-podcast analysis updated weekly.
You're clearly into How I AI.
Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime