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._

Claire VohostMichal Peledguest

Dec 8, 202558mWatch on YouTube ↗

EPISODE INFO

Released: December 8, 2025
Duration: 58m
Channel: How I AI
Watch on YouTube: ▶ Open ↗

EPISODE DESCRIPTION

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 missed
The step-by-step process for turning static customer research into interactive AI personas that product and marketing teams can actually use
Why NotebookLM excels at creating prompts from source material with proper citations
How to structure agent-mode prompts to create effective “little helpers” that follow your exact workflow
A practical framework for improving your prompts when AI tools aren’t giving you the results you want
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._

SPEAKERS

Claire Vo
host
Michal Peled
guest

EPISODE SUMMARY

In this episode of How I AI, featuring Claire Vo and Michal Peled, ChatGPT agent mode: The “little helper” that transformed recruiting & solved parking nightmares explores chatGPT agent mode automates recruiting, personas, and parking planning workflows The episode introduces ChatGPT “agent mode” as a practical way to offload repetitive, high-friction work by letting ChatGPT browse sites, log in, and take actions with human handoff points.

RELATED EPISODES