🎙️This week on How I AI: Which AI model is the best designer? and ChatGPT agent mode, the “little helper” that transformed recruiting

Your weekly listens from How I AI, part of the Lenny’s Podcast Network

Every Monday, host Claire Vo shares a 30- to 45-minute episode with a new guest demoing a practical, impactful way they’ve learned to use AI in their work or life. No pontificating—just specific and actionable advice.

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

Brought to you by:

• Brex—The intelligent finance platform built for founders

• Google Gemini—Your everyday AI assistant

In this episode, Michal Peled walks through three real examples from her work at HoneyBook—using ChatGPT’s agent mode to automate LinkedIn recruiting (and surface candidates humans missed), turning static customer research into interactive AI personas, and even building a parking-avoidance calendar app for Giants games. Along the way, Michal breaks down how to structure great agent workflows, why interviewing humans is the key to good automation, and how tools like NotebookLM can turn messy research into reliable, citation-backed prompts.

Biggest takeaways:

1. ChatGPT agent mode is your “little helper” that can perform real-world tasks. Unlike regular ChatGPT, agent mode can navigate websites, perform searches, and execute complex workflows—all while narrating its thought process. This transforms it from a text generator into a true digital assistant that can replicate human workflows.

2. The best AI automation starts with interviewing humans about their process. Michal’s recruiting automation succeeded because she asked the hiring team exactly what criteria they use: “Candidates must be from Israel or working at an Israeli company, active on LinkedIn within 3 months, and employed at their current job for over a year.” By codifying these specific requirements, she created an agent that found candidates the team had missed.

3. The best prompt improvement technique: ask AI to fix your prompt. When AI isn’t giving you the results you want, Michal’s approach is to say: “This is the prompt I’m using. This is what’s wrong with the output. This is how I want it to be. Take away everything that doesn’t work well.”

▶️ Listen now on YouTube | Spotify | Apple Podcasts

Gemini 3 vs. Claude Opus 4.5 vs. GPT-5.1 Codex: Which AI model is the best designer?

Brought to you by: Lovable—Build apps by simply chatting with AI

In this episode, Claire runs a simple but revealing experiment: give the exact same prompt to three leading AI models—Gemini 3, Claude Opus 4.5, and GPT-5.1 Codex—and see which is actually good at design. One model produces a polished, thoughtful, near-production-ready redesign. One delivers something usable but uninspired. And one . . . reminds us that strong coding ability doesn’t always translate to front-end taste. If you’ve ever wondered which AI you should trust with real design work, this episode gives you the clearest answer yet.

Biggest takeaways:

1. Anthropic’s Opus 4.5 is the clear design winner. It delivered the most visually appealing and functionally complete redesign, with thoughtful details like hover effects with call-to-action arrows, placeholder images for missing content, and elegant background imagery instead of generic gradients.

2. Codex 5.1 struggles with front-end design. Despite its strong coding capabilities, OpenAI’s model delivered the weakest design, falling back on “AI slop purple gradients” and creating non-functional elements. The lesson: don’t use it as your design resource.

3. Gemini 3 is serviceable but lacks refinement. While it created a functional redesign with hero sections and card layouts, it missed opportunities for visual polish and didn’t handle edge cases (like missing images) as elegantly as Opus 4.5.

▶️ Listen now on YouTube | Spotify | Apple Podcasts

---

More shows coming soon. . . 👀
If you’re enjoying these episodes, reply and let me know what you’d love to learn more about: AI workflows, hiring, growth, product strategy—anything.

Catch you next week,
Lenny

P.S. Want every new episode delivered the moment it drops? Hit “Follow” on your favorite podcast app.