Skip to main content
How I AI

How to turn Claude Code into your personal life operating system | Hilary Gridley

51 min episode · 2 min read
·

Episode

51 min

Read time

2 min

AI-Generated Summary

Key Takeaways

  • Automation Decision Framework: For any task, ask whether being 10x better at it would produce 10x the impact. If no, automate it entirely. If yes, invest human time there. This applies within tasks too — giving a talk means automating slide-building but keeping idea generation and narrative crafting as human work.
  • Preference Learning Over Upfront Configuration: Rather than defining scheduling preferences in advance, let Claude Code observe actual daily behavior over time and build the preferences file itself. Self-reported preferences (like "60-minute daily walk") rarely reflect reality, while observed patterns — such as avoiding deep work before bed — do.
  • Janky-First Workflow Development: Test any new AI workflow in its simplest, most manual form for at least one week before connecting APIs, OAuth integrations, or calendar hooks. Hilary estimates only roughly 20% of workflow ideas she tests actually get continued use, making upfront integration setup wasteful for the majority that get abandoned.
  • "Yapper's API" as Integration Substitute: Instead of building technical integrations between tools, simply narrate what is visible on screen directly to Claude Code. Describing a document being written, a task completed, or a calendar screenshot provides sufficient context for Claude to log activity, update files, and track progress without any programmatic data connection.
  • Problem-Statement-First Skill Building: Start with a plain-language description of a problem — such as forgetting product return deadlines — and let Claude Code ask clarifying questions, then build the script and slash-command skill file itself. The resulting skill file contains readable English instructions plus executable code, requiring zero prior programming knowledge to initiate.

What It Covers

Entrepreneur and new mom Hilary Gridley demonstrates how she uses Claude Code via terminal to manage her daily schedule, to-do list, and personal workflows — building an adaptive, low-setup "anti-system system" that learns from observed behavior rather than pre-configured rules or complex integrations.

Key Questions Answered

  • Automation Decision Framework: For any task, ask whether being 10x better at it would produce 10x the impact. If no, automate it entirely. If yes, invest human time there. This applies within tasks too — giving a talk means automating slide-building but keeping idea generation and narrative crafting as human work.
  • Preference Learning Over Upfront Configuration: Rather than defining scheduling preferences in advance, let Claude Code observe actual daily behavior over time and build the preferences file itself. Self-reported preferences (like "60-minute daily walk") rarely reflect reality, while observed patterns — such as avoiding deep work before bed — do.
  • Janky-First Workflow Development: Test any new AI workflow in its simplest, most manual form for at least one week before connecting APIs, OAuth integrations, or calendar hooks. Hilary estimates only roughly 20% of workflow ideas she tests actually get continued use, making upfront integration setup wasteful for the majority that get abandoned.
  • "Yapper's API" as Integration Substitute: Instead of building technical integrations between tools, simply narrate what is visible on screen directly to Claude Code. Describing a document being written, a task completed, or a calendar screenshot provides sufficient context for Claude to log activity, update files, and track progress without any programmatic data connection.
  • Problem-Statement-First Skill Building: Start with a plain-language description of a problem — such as forgetting product return deadlines — and let Claude Code ask clarifying questions, then build the script and slash-command skill file itself. The resulting skill file contains readable English instructions plus executable code, requiring zero prior programming knowledge to initiate.

Notable Moment

Hilary reveals that her Claude Code system identified a recurring pattern she had not consciously noticed: despite listing three daily priorities each morning, only the first priority consistently received real time. Claude then reframed the actual question — whether she was selecting the right number-one priority each day.

Know someone who'd find this useful?

You just read a 3-minute summary of a 48-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

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

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