AI as a Strategic Thought Partner with UX Implications

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: ProductTalk.org

• Follow Petra Wille: Petra-Wille.com

Mentioned in the episode:

• ChatGPT (chatgpt.com)

• Claude (claude.ai) & Claude Code (anthropic.com/claude-code) (Anthropic (anthropic.com))

• WisprFlow (wisprflow.ai)

• Petra Wille’s Leadership Email Course (petra-wille.com/course-info-strong-to-exceptio…)

• Petra’s Blog (petra-wille.com/blog)

• Vibe coding (en.wikipedia.org/wiki/Vibe_coding)

• Python (python.org)

• Node.js

• Teresa Torres’ Building My First AI Product: 6 Lessons from My 90-Day Deep Dive (producttalk.org/2025/08/ai-playbook) blog post

• Concepts: RAG (retrieval-augmented generation) (en.wikipedia.org/wiki/Retrieval-augmented_gene…), MCP (Model Context Protocol) (en.wikipedia.org/wiki/Model_Context_Protocol), agents and workflows

• Subagents (docs.anthropic.com/en/docs/claude-code/sub-age…)

• Teresa’s Product Talk blog (producttalk.org/2025/08/ai-playbook)

• Teresa’s Product in Practice: Getting Started with Several APIs (And the Challenges I Faced) (producttalk.org/2025/04/api-challenges) blog post