Skip to main content
How I AI

How Webflow’s CPO built an AI chief of staff to manage her calendar, prep for meetings, and drive AI adoption | Rachel Wolan

43 min episode · 2 min read
·

Episode

43 min

Read time

2 min

Topics

Artificial Intelligence

AI-Generated Summary

Key Takeaways

  • Personal AI Chief of Staff: Wolan built a locally-hosted app using Claude Code that connects to Google Calendar and Gmail via API tokens with limited permissions (read-only calendar, draft-only email) to analyze her schedule, suggest delegations, and flag overcommitment patterns weekly.
  • Markdown-Powered Personal Apps: Store context as markdown files in your repo instead of databases—personal notes, meeting prep, product updates—so any AI agent can reference them across tools while displaying nicely on front-end interfaces without infrastructure complexity.
  • Builder Day Framework: Run organization-wide prototype days where all teams stop regular work to build with AI tools (Cursor, Figma, Webflow). Provide warm-up assignments, on-call engineer support, judging panels with executives, prizes, and measure sustained adoption post-event to drive 80-plus prototypes.
  • Quantified Prompting Technique: When AI outputs miss the mark, clear context and restart with numerical modifiers—"be 10x more detailed" for incremental changes or "100x more harsh" for complete rewrites—because language models calibrate better to specific numerical targets than vague requests.

What It Covers

Webflow CPO Rachel Wolan demonstrates her custom-built AI chief of staff that manages her calendar, preps meetings, triages email, and explains her framework for driving AI adoption through builder days across product teams.

Key Questions Answered

  • Personal AI Chief of Staff: Wolan built a locally-hosted app using Claude Code that connects to Google Calendar and Gmail via API tokens with limited permissions (read-only calendar, draft-only email) to analyze her schedule, suggest delegations, and flag overcommitment patterns weekly.
  • Markdown-Powered Personal Apps: Store context as markdown files in your repo instead of databases—personal notes, meeting prep, product updates—so any AI agent can reference them across tools while displaying nicely on front-end interfaces without infrastructure complexity.
  • Builder Day Framework: Run organization-wide prototype days where all teams stop regular work to build with AI tools (Cursor, Figma, Webflow). Provide warm-up assignments, on-call engineer support, judging panels with executives, prizes, and measure sustained adoption post-event to drive 80-plus prototypes.
  • Quantified Prompting Technique: When AI outputs miss the mark, clear context and restart with numerical modifiers—"be 10x more detailed" for incremental changes or "100x more harsh" for complete rewrites—because language models calibrate better to specific numerical targets than vague requests.

Notable Moment

Wolan's AI chief of staff analyzes her calendar and delivers brutal feedback that she operates like a senior PM rather than a CPO, spending time reviewing PRDs and recording marketing videos instead of strategic work—forcing honest reflection on executive time allocation.

Know someone who'd find this useful?

You just read a 3-minute summary of a 40-minute episode.

Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

More from How I AI

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's AI & Machine Learning Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into How I AI.

Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for up to 3 shows.

Start My Monday Digest

No credit card · Unsubscribe anytime