How to Turn Claude Code into Your Personal Life Operating System

Guest: Hilary Gridley

Host: Claire Vo

Podcast: How I AI

Date: March 30, 2026

Episode Overview

This episode dives deep into Hilary Gridley’s "anti-system system" for using AI—specifically Claude Code—to manage the chaos of modern life, both as an entrepreneur and a new mom. Instead of building complex productivity frameworks, Hilary illustrates how minimal effort combined with smart workflows and AI observation can radically boost efficiency and reclaim lost time. She describes her frictionless, iterative approach, showing practical shortcuts, her unique automation philosophy, and details how anyone—even those intimidated by code—can use AI-powered agents to streamline their daily routines.

Key Discussion Points & Insights

1. The Motivation Behind Automating with AI

• Hilary describes the sky-high opportunity cost of her time now as a new parent and entrepreneur:
  • "Also as a new mom, it's never been harder. It has never felt harder to get out of my time what I want to because my attention is super fractured." (00:00–00:15)
• Philosophy: Delegate or automate anything that doesn’t require you to be uniquely excellent.
  • "For any possible task? If I were 10 times better at it, would it have 10 times the impact? If the answer to that is no, then I just automate it. And if the answer to that is yes, those are the things that I want to put more time and effort into." (00:15–00:32)
• Hilary’s system is built around minimizing setup and maintenance, focusing on real-life observation and iteration.

2. The Anti-System System Approach

2.1. Streamlining Intake: No-Fuss To-Do Capture

• Low-friction reminders: Double-tap the back of the phone to dictate a task (e.g., "reschedule pediatrician appointment").
  • "I just have a shortcut right on my phone... double tap the back of the phone and then it pulls up a dictation box and I just say..." (09:31–10:58)
• Setup instructions are provided via a Figma file for listeners for easier replication. (11:08)

2.2. Claude Code: Planning & Running Daily Life via Terminal

• Hilary uses Claude Code through the terminal for life management.
• The system auto-collects and organizes reminders, tasks, and preferences as Markdown files—no manual editing required.
  • "Claude is in the background taking those reminders and putting them into a doc where it’s organizing them based on category..." (13:31–14:00)
• Hilary intentionally doesn’t micro-manage the agent’s internal docs—treats the agent like an autonomous employee.
  • "It’s none of my business how Claude gets its work done." (14:12–14:45)
• Dynamic observation for preferences and schedules—Claude observes actual behavior and learns from real outcomes (vs. static, aspirational preferences).
  • "This has just been the AI observing me over time and changing based on things that it is observing..." (15:30–16:45)

3. How the System Builds & Adjusts Itself

• The system logs both “planned” and “actual” activity in daily notes.
  • "It has what I said I was going to do on the day and then it has what I’m actually doing." (23:53–25:30)
• Regular retrospectives: Hilary checks gaps between intention and execution, using AI summaries & reflections.
  • "Claude is pointing out that neither of those things are really working. So we adjust as we go..." (27:20–27:45)
• Habit of using Yappers API: Just verbally report completed tasks to the AI as you go about your day—no need to over-automate.
  • "I do believe in my heart of hearts in the Yappers API, which is when I’m looking at things on one screen and I am talking about what I’m seeing to another screen..." (23:53)

4. Minimum Viable Complexity: Only Expand Workflows That Prove Useful

• Test janky, simple versions first, only add complexity once proven valuable.
  • “I have a hit rate of maybe 20%. A lot of things where I’m like, oh, I think it would be helpful to set up this type of workflow. I don’t actually end up using it.” (29:46–30:50)
• Screenshot/voice note sharing is recommended over waiting for ideal API/data integrations—operate with what you have and iterate up.

5. Deciding What to Automate vs. Do Yourself

5.1. Hilary’s Impact Framework

• "For any possible task, if I were 10 times better at it, would it have 10 times the impact?" (33:43)
  • If yes: Spend time and effort here (e.g., writing, creative strategy).
  • If no: Automate it (e.g., logistics, admin, returns).

5.2. Life and Work Examples

• She breaks down even complex tasks (like producing a talk) into components—only automating repetitive, low-value steps.
• Learning Curve Nuance: New tasks shouldn’t be automated for beginners; mastery justifies automation.
  • “This framework is very... it can change depending where you are on learning curves.” (37:51–38:52)

6. “Recording Mode” Skill: Demo and Privacy by Design

• Hilary created a Claude Code “recording on” skill for demos—auto-replaces sensitive terms and maintains workflow authenticity, which she uses in public settings or podcasts.
  • “Anytime it’s going to pull up any identifying information, it just changes it before it puts it on my screen.” (41:12–42:17)
• Lessons for B2B product demos: Smart anonymization can allow live demonstration with real data (e.g., a “toggle” for redacting sensitive info).
  • “Brilliant 10 out of 10 idea. We’re gonna clip this one for TikTok...” (42:17–43:32)

7. Real-World Problem Solving Using Claude Code

7.1. Returns Example

• Hilary describes her product management style: Just state a problem in plain language, let Claude solve and implement the workflow (e.g., auto-manage and warn about returns).
  • "I keep forgetting to return things on time. Also, I hate them. Just have to get that off my chest. I want you to come up with some solutions to make this easier for me. What do you got?" (44:53–45:33)
• Claude iterates, asks questions, and builds tailored skills/scripts on-the-fly—demonstrating real agentic utility.

8. Encouragement and Recommendations for Beginners

• Overcoming Terminal/Code Fear
  • “Just try to do one thing with it every day... you just need to build the muscle memory.” (49:11)
  • Even originally hesitant users will quickly absorb the value once they get over the initial hurdle.

Quotes & Memorable Moments

• “Within me there are two wolves and neither of those wolves are life admin.” — Hilary Gridley (06:14)
• “Complexity has to earn its keep.” — Hilary Gridley (29:46)
• “If I were 10 times better at it, would it have 10 times the impact?” — Hilary Gridley (00:15, 33:43)
• “I have a hit rate of maybe 20%... if I spent all this time upfront getting all of these things connected... it’s a waste of time.” (29:46)
• “You don’t have to start with a big complex Python script... just start with a problem statement.” — Claire Vo (47:56)
• “I always reason from first principles because I have no idea what I’m doing. And that’s how I feel when I talk to Claude: I don’t know how this works, fix it.” — Hilary Gridley (43:36)
• “You can preemptively solve problems you might have with AI in a very low-cost way.” — Claire Vo (47:56)
• “I was one of those people who was like, I’m never going to work in the terminal, just a non-starter for me. And the only reason I did was because I was using Cursor... but then eventually I got used to the terminal and realized the incredible power that it has.” — Hilary Gridley (49:11–50:18)

Notable Timestamps

• 00:00–00:32: Hilary’s time constraints and automation philosophy
• 09:31–11:08: Frictionless reminders with phone shortcuts
• 13:31–14:00: Claude organizing tasks via Markdown/text files
• 14:12–14:45: Treating AI agents as employees—trusting them with process
• 23:53–25:30: Logging planned vs. actual activity; the daily AI-powered “retrospective”
• 29:46–30:50: Justifying complexity, why to iterate before automating
• 33:43–36:21: The “10x impact” framework for automation
• 41:12–42:17: The “recording mode” demo—automated anonymization
• 44:53–45:33: Product managing Claude—problem statement to real automation
• 49:11–50:18: Building muscle memory with intentional daily use

Actionable Takeaways

• Start with simple, lightweight workflows (voice notes, screenshots) to test value.
• Only add complexity if you consistently miss the simple version’s limits.
• Frame tasks through Hilary’s “10x impact” lens to focus on what only you can do.
• Treat AI agents as team members—give them autonomy and let them optimize the process.
• Build comfort and skill by doing one new small thing daily with AI tools like Claude Code.

Links & Resources

• Hilary Gridley’s Substack
• Figma template for phone shortcut setup (as promised by Hilary)
• How I AI Podcast

Summary prepared by How I AI Summaries — demystifying the workflows that drive the future of productivity.