How do you role-play AI for audience perspective checks?

In this episode:

• Petra’s voice-first workflow and how she uses AI to mine her own archive for consistency
• Teresa’s Claude Code setup: planning mode, context from local files, and project planning before writing code
• Using AI as an editor and reviewer rather than as a ghostwriter
• Creating sub-agents (copy editor, skeptic, devil’s advocate) to critique drafts
• How ChatGPT and Claude differ in strengths (structure vs. tone)
• The shift toward personal agents as the interface for products

Resources & Links:

• Follow Teresa Torres: https://ProductTalk.org
• Follow Petra Wille: https://Petra-Wille.com

Mentioned in the episode:

• ChatGPT
• Claude & Claude Code (Anthropic)
• WisprFlow
• Petra Wille’s Leadership Email Course
• Petra’s Blog
• Vibe coding
• Python
• Node.js
• Teresa Torres’ Building My First AI Product: 6 Lessons from My 90-Day Deep Dive blog post
• Concepts: RAG (retrieval-augmented generation), MCP (Model Context Protocol), agents and workflows
• Subagents
• Teresa’s Product Talk blog
• Teresa’s Product in Practice: Getting Started with Several APIs (And the Challenges I Faced) blog post