How I AI

ChatGPT agent mode: The “little helper” that transformed recruiting & solved parking nightmares

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:* 1. How to use ChatGPT agent mode to automate LinkedIn recruiting and find high-quality candidates that manual searches missed 2. The step-by-step process for turning static customer research into interactive AI personas that product and marketing teams can actually use 3. Why NotebookLM excels at creating prompts from source material with proper citations 4. How to structure agent-mode prompts to create effective “little helpers” that follow your exact workflow 5. A practical framework for improving your prompts when AI tools aren’t giving you the results you want 6. How internal tools teams can drive massive impact by focusing on eliminating friction in everyday workflows *Brought to you by:* Brex—The intelligent finance platform built for founders: https://brex.com/howiai Google Gemini—Your everyday AI assistant: https://ai.dev/ *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 jordan@penname.co._

CVClaire VohostMPMichal Peledguest

Dec 8, 2025·58m·Watch on YouTube ↗

📖 CHAPTERS

1. 1

   What ChatGPT agent mode is—and why Michal needed it for real work

   Claire introduces ChatGPT’s agent mode (agentic browsing) and Michal explains the core problem: talented teams lose hours to repetitive, manual tasks just to gather information. For recruiting, the key requirement was not just web search, but logging into LinkedIn and taking actions like a human would.

2. 2

   Designing the recruiting agent: “little helper” prompt structure and constraints

   Michal walks through how he built an effective agent prompt by first setting a role (“You are an IT recruiter”), then defining an explicit task flow, then adding hiring-team-specific constraints. Claire highlights how interviewing colleagues to capture their step-by-step process is often enough to automate meaningful work.

3. 3

   Agent mode in action: watching it browse LinkedIn like a human operator

   They demo the agent navigating LinkedIn: reading the job description, opening LinkedIn, searching, clicking through results, and evaluating profiles. Claire notes how surprising this “magic computer” experience can be for non-technical users and calls out the UX design choices that make agent browsing understandable and usable.

4. 4

   Output format that recruiters can trust: ranked candidates + anonymization

   Michal shows an example result: five candidates returned within about ten minutes, with match scores and links. They discuss why scoring helps compare options, and why anonymizing candidate info can reduce bias and focus reviewers on qualifications against stated criteria.

5. 5

   Team validation and impact: quality wins, not just speed

   Michal sanity-checks the AI’s first output by sending it to the hiring manager for evaluation. The manager reports that four of five were strong fits they hadn’t found manually, which builds trust and leads to expanding the workflow across more roles.

6. 6

   From research PDFs to “talking” personas: the goal for custom GPTs

   The conversation shifts from finding real people to creating interactive buyer-persona GPTs. HoneyBook had extensive, expensive customer research trapped in documents, so the goal became making those personas conversational and easy to consult during product and marketing decisions.

7. 7

   Using NotebookLM to convert source research into persona prompts

   Michal uses Google’s NotebookLM because it can be constrained to user-provided sources and provide citations. He prompts it as an expert prompt engineer to generate highly detailed persona instructions—while explicitly forbidding invention beyond what’s written or implied in the research.

8. 8

   Refining prompts for production: length limits and persona guardrails

   The initial persona prompts needed tightening: some exceeded ChatGPT’s custom GPT instruction limits and lacked behavioral guardrails. Michal refines using ChatGPT and sometimes Claude, adding boundaries to keep the personas safe, focused, and consistent at scale.

9. 9

   Demo: brainstorming with different persona GPTs for marketing copy

   Michal demonstrates asking persona GPTs for ad headlines that would catch their attention during a busy workday. Different personas return distinct headline styles and explain the reasoning, letting teams test messaging against customer mindsets quickly.

10. 10

    Solving SF parking chaos: Giants game schedule → Google Calendar ICS automation

    Michal tackles a very practical operations problem: parking near Oracle Park spikes dramatically on day games. He uses ChatGPT to find relevant home games within a time window and generate a filtered ICS calendar file that flags high-risk parking days without blocking availability.

11. 11

    Lightning round: internal automation roles, prompting habits, and a rewrite template

    They close with a discussion of Michal’s role as a Technical Operations Engineer building and enabling internal tooling. Michal shares his go-to prompting technique: ask the model to rewrite the prompt by specifying what’s wrong, what “right” looks like, and explicitly granting permission to delete/replace parts of the original.