How I AI

Teresa Torres is the author of Continuous Discovery Habits and an internationally acclaimed speaker and coach. In this episode, Teresa demonstrates how she’s built a personalized productivity system using Claude Code to manage her tasks, automate research collection, and improve her writing. She shows how non-developers can leverage AI tools to create personalized workflows that match their unique needs and thinking style.

What you’ll learn:
How Teresa built a personalized task management system in Claude Code that matches her exact workflow needs
Why she moved from Trello to a markdown-based system that gives her complete control and searchability
How she automated academic research collection with daily digests of relevant papers
Her strategy for organizing context files to make Claude more effective without overwhelming it
Why “pair programming” with Claude has become her approach to everything from writing to task management
How she uses Claude as a writing partner while maintaining her authentic voice
The power of slash commands and automation to reduce friction in daily workflows
—
Brought to you by:
Brex—The intelligent finance platform built for founders
Graphite—The next generation of code review
—
In this episode, we cover:
(00:00) Introduction to Teresa Torres
(02:10) Why Claude Code became Teresa’s productivity tool of choice
(03:00) The evolution from browser-based AI to terminal-based workflows
(04:14) Demo: Creating a personalized task management system
(07:52) How the task system works with markdown files and Obsidian
(12:56) Quick recap
(14:13) Taking notes within tasks for better searchability
(15:54) Demo: Automated research digest workflow
(19:32) How the research plugin searches and summarizes academic papers
(24:43) Filtering overwhelming information sources
(29:00) Using small, focused context files instead of one large document
(32:58) Claude as a writing partner: review, research, and refinement
(35:34) Recap of workflows and lightning round
—
Tools referenced:
• Claude Code: https://claude.ai/
• Obsidian: https://Obsidian.md/
• VS Code: https://code.visualstudio.com/
• Descript: https://www.descript.com/
• ChatGPT: https://chat.openai.com/
• Trello: https://trello.com/
—
Other references:
• Continuous Discovery Habits: https://www.producttalk.org/continuous-discovery-habits/
• Google Scholar: https://scholar.google.com/
• Claude Code: What It Is, How It’s Different, and Why Non-Technical People Should Use It: https://www.producttalk.org/claude-code-what-it-is-and-how-its-different
—
Where to find Teresa Torres:
Blog: https://producttalk.org/
Podcast: https://justnowpossible.com/
Book: https://www.amazon.com/Continuous-Discovery-Habits-Discover-Products/dp/1736633309
LinkedIn: https://www.linkedin.com/in/teresatorres/
—
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].

Alexander Embiricos, the product lead for Codex at OpenAI, shares practical workflows for getting the most out of this AI coding agent. In this episode, he demonstrates how both non-technical users and experienced engineers can leverage Codex to accelerate development, from making simple code changes to building production-ready applications. Alex walks through real examples of using Codex in VS Code and terminal environments, implementing parallel workflows with Git worktrees, and creating detailed implementation plans for complex projects. He also reveals how OpenAI uses Codex internally, including how they built the Sora Android app in just 28 days, and offers insights on automated code review and the future of AI-assisted development.

What you’ll learn:
How to set up and use Codex in VS Code and terminal environments for both simple and complex coding tasks
A practical workflow for running multiple Codex instances in parallel using Git worktrees to avoid conflicts
How to create detailed implementation plans using the Plans.md technique for complex engineering projects
Why context is critical when prompting Codex—and how to provide the right information for better results
How OpenAI uses automated code review to accelerate development while maintaining high quality standards
The key differences between vibe coding for prototypes versus building production-ready applications with AI
How the new GPT-5.2 model improves Codex’s capabilities with faster reasoning and better problem-solving
—
Brought to you by:
Brex—The intelligent finance platform built for founders
Graphite—Your AI code review platform
—
Detailed workflow walkthrough from this episode:
https://chatprd.ai/how-i-ai/advanced-codex-workflows-with-openai-alex-embiricos
—
In this episode, we cover:
(00:00) Introduction to Alex and Codex
(02:06) Getting started with Codex
(04:54) Using Codex for parallel tasks
(07:34) Understanding Git worktrees
(09:51) Terminal shortcuts and command-line efficiency
(12:16) How OpenAI built the Sora Android app with Codex
(15:37) Using PLANS.md for problem solving
(17:57) The importance of high agency
(22:22) Deciding between what needs a plan and what doesn’t
(26:42) How to multiply the impact of Codex
(28:08) Implementing automated code review with GitHub
(31:58) Delivering the benefits of AGI to all humanity
(34:35) Accelerating developer productivity
(36:38) Recap and final thoughts
—
Tools referenced:
• Codex: https://openai.com/blog/openai-codex
• VS Code: https://code.visualstudio.com/
• Cursor: https://cursor.com/
• Git: https://git-scm.com/
• GitHub: https://github.com/
• Atlas: https://openai.com/atlas
• ChatGPT: https://chat.openai.com/
• Slack: https://slack.com/
• Linear: https://linear.app/
—
Other references:
• Sora Android app: https://openai.com/blog/sora
• GPT-5.2 model: https://openai.com/index/introducing-gpt-5-2/
• SWE-bench: https://openai.com/index/introducing-swe-bench-verified/
—
Where to find Alexander Embiricos:
LinkedIn: https://www.linkedin.com/in/embirico
X: https://x.com/embirico
—
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].

Wade Foster is the co-founder and CEO of Zapier. In this episode, Wade shows how he uses meeting transcripts, Zapier agents, and even Grok to analyze company culture, evaluate interview candidates, and source talent from unexpected places. He explains why CEOs need to lead by example when it comes to AI adoption and shares practical workflows that any executive can implement to make hiring more effective and efficient.

What you’ll learn:
How to use meeting transcripts to extract your company’s “unspoken culture” and compare it against your stated values
A workflow for creating AI interview evaluators that assess candidates against your job descriptions and company values
How to use Zapier agents to provide objective feedback on candidate interviews while checking your own biases
Why CEOs should participate in AI “hackathons” and “show and tells” rather than just delegating AI adoption
A surprising technique for using Grok to find “diamonds in the rough” talent outside traditional recruiting channels
How AI enables companies to complete tasks that were previously not economically viable
—
This entire episode is brought to you by:
Brex—The intelligent finance platform built for founders
—
In this episode, we cover:
(00:00) Introduction to Wade Foster
(02:32) Zapier’s AI adoption
(06:50) Creating AI fluency rubrics
(08:37) Using Granola to extract company culture from meeting transcripts
(10:49) Practical use cases for company culture rubrics
(13:38) Building an AI interview evaluation agent in Zapier
(16:50) Using Copilot to improve agent prompts
(18:49) Ideas for enhancing the interview agent
(22:31) Mistakes people make when using agents
(25:11) Using Grok to find talent on social media platforms
(33:39) Recap of AI workflows for recruiting and hiring
(34:40) Lightning round and final thoughts
—
Tools referenced:
• Zapier: https://zapier.com/
• Zapier Agents: https://zapier.com/agents
• Granola: https://granola.ai/
• Grok: https://grok.x.ai/
• ChatGPT: https://chat.openai.com/
• Copilot: https://copilot.microsoft.com/
—
Other references:
• Zapier values: https://zapier.com/about
• How Zapier’s EA built an army of AI interns to automate meeting prep, strengthen team culture, and scale internal alignment | Cortney Hickey: https://www.lennysnewsletter.com/p/how-zapiers-ea-built-an-army-of-ai
• How this CEO turned 25,000 hours of sales calls into a self-learning go-to-market engine | Matt Britton (Suzy): https://www.lennysnewsletter.com/p/how-this-ceo-turned-25000-hours-of
—
Where to find Wade Foster:
Zapier: https://zapier.com/
LinkedIn: https://www.linkedin.com/in/wadefoster/
X: https://twitter.com/wadefoster
—
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].

Rachel Wolan, the chief product officer at Webflow, has embraced AI not just as a product leader but as a hands-on builder. A coder since age 16, Rachel has returned to her technical roots by creating a custom AI chief-of-staff application that helps manage her executive workload. In this episode, she demonstrates how she uses personal AI software to prep for meetings, triage her calendar, manage emails, and even get brutally honest feedback about how she’s spending her time.

What you’ll learn:
How Rachel built a custom AI chief-of-staff application that integrates with her calendar, email, and more
Why building personal software can be a gateway to understanding AI’s capabilities for executives
How her AI agents help her prep for podcasts, dinners, and meetings with just-in-time information
The technical approach to building personal AI software using markdown files, API tokens, and multiple LLM interfaces
How Rachel organized company-wide “builder days” that dramatically increased AI tool adoption across her organization
Why she believes executives must lead by example in AI adoption to authentically drive organizational change
—
Brought to you by:
Graphite—Your AI code review platform
Atlassian for Startups —From MVP to IPO
—
In this episode, we cover:
(00:00) Introduction to Rachel Wolan
(02:26) Why Rachel started leaning into AI
(06:26) Building an AI chief of staff
(08:17) Prepping for the podcast
(10:00) Rachel’s morning flow with her AI chief of staff
(14:14) Designing a personalized interface with custom note cards
(16:34) Getting “brutal truth” feedback from your AI assistant
(19:34) Email triage and management workflows
(23:31) Prepping for networking dinners and events
(28:18) The result of building an AI chief of staff
(30:09) Organizing “builder days” to drive AI adoption
(35:38) Measuring the impact of AI adoption initiatives
(38:00) Lightning round and final thoughts
—
Tools referenced:
• Claude: https://claude.ai/
• Claude Code: https://claude.ai/code
• Cursor: https://cursor.com/
• Google Calendar API: https://developers.google.com/calendar
• Gmail API: https://developers.google.com/gmail
• Webflow: https://webflow.com/
• Figma: https://www.figma.com/
• Make: https://www.make.com/
• Hex: https://hex.tech/
—
Where to find Rachel Wolan:
LinkedIn: https://www.linkedin.com/in/rachelwolan/
X: https://x.com/rachelwolan
Webflow: https://webflow.com
—
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].

Brian Greenbaum is a Senior Staff Product Designer at Pendo who led a company-wide AI transformation after a personal epiphany while on paternity leave. After experiencing the power of AI coding tools firsthand, he created a structured approach to help his entire product organization adopt AI. In this episode, Brian shares his complete playbook for driving AI adoption across teams, measuring success, and navigating the organizational challenges that come with new technology adoption.

What you’ll learn:
The exact Slack message Brian sent while on paternity leave that kickstarted his company’s AI transformation
How to structure both synchronous and asynchronous AI learning opportunities for maximum adoption
The two-pronged approach that dramatically increased AI tool usage across teams
Why becoming your company’s AI champion is one of the best career moves you can make right now
How to measure AI adoption success with sentiment surveys and clear metrics
The critical role of creating a “golden path” for AI tool usage with legal, security, and finance teams
—
Brought to you by:
Google Gemini—Your everyday AI assistant
Lovable—Build apps by simply chatting with AI
—
In this episode, we cover:
(00:00) Introduction to Brian Greenbaum
(01:38) Brian’s paternity leave epiphany that sparked an AI initiative
(05:00) Sending the message that launched a transformation
(12:25) The two-pronged approach: synchronous and asynchronous learning
(17:29) Encouraging experimentation and creative exploration
(18:41) How AI enables designers to move beyond MVP thinking
(22:00) Quick summary of the two-pronged approach
(24:43) Measuring AI adoption
(33:48) Creating a centralized AI knowledge center
(35:58) Building an MCP server to demonstrate AI’s potential
(44:08) Why technical understanding is crucial for non-technical roles
(46:01) Final thoughts
—
Tools referenced:
• Cursor: https://cursor.com/
• Bolt.new: https://bolt.new/
• Claude: https://claude.ai/
• ChatGPT: https://chat.openai.com/
• Midjourney: https://www.midjourney.com/
• Gemini: https://gemini.google.com/
—
Other references:
• Pendo: https://www.pendo.io/
• Confluence: https://www.atlassian.com/software/confluence
• Slack: https://slack.com/
—
Where to find Brian Greenbaum:
LinkedIn: https://www.linkedin.com/in/briangreenbaum/
—
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].