Set Up Frictionless Task Capture
Create an iPhone Shortcut with Dictate Text and append the result to one Reminders list or text inbox. Assign it to Back Tap or the lock screen so a thought can become a task without opening an app.
Capture loose tasks by speaking into an iPhone Shortcut, then let Claude Code turn the inbox, your calendar, and learned preferences into a realistic day. Large tasks become one small scheduled action, and a simple activity log helps the plan improve from what you actually do.


Source episode · 09:30
How I AI: Hilary Gridley’s “Anti-System” for Automating Life with Claude Codewith Claire Vo
Hilary captures tasks from her iPhone lock screen, asks Claude Code to plan her day, and lets it compare the resulting calendar with a running log of what she actually completes.
A realistic calendar plan that schedules small next actions, preserves existing commitments, and records what actually happened.
Anthropic AI assistant
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
Create an iPhone Shortcut with Dictate Text and append the result to one Reminders list or text inbox. Assign it to Back Tap or the lock screen so a thought can become a task without opening an app.
Run the planning command in Claude Code. It should load the capture inbox, current calendar, and the Markdown file where it keeps practical scheduling preferences.
plan my day
Tell Claude the one or two outcomes that matter today. For anything large or repeatedly postponed, have it choose the smallest useful first action and place that action on the calendar.
My main outcome today is [priority]. I also need to handle [secondary task]. Use my reminders, calendar, and current preferences to build a realistic plan. If a task is too large for one block, schedule only the first concrete action. Leave transition time between commitments.
Keep Claude open while you work and give it short updates when plans change or tasks finish. It records those observations in the daily note so the system learns from actual behavior.
Ask Claude to compare the planned calendar with the activity log. Use repeated gaps to update the preference file and improve the next plan, without turning the reflection into another required ritual.
Compare today's plan with what I actually did. What repeatedly received less or more time than expected? Which constraints or preferences should you update before planning tomorrow? Change only patterns supported by today's log or repeated prior observations.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building

Quickly analyze thousands of YouTube comments for sentiment and new content ideas using the Jev AI model. This workflow helps creators turn audience feedback into actionable insights for their content strategy.

Create a powerful product insights engine by combining Jev with other LLMs. Use Jev for large-scale classification of customer feedback and development data, then apply reasoning models to analyze the structured output for deep insights.

Use the Jev AI model to cheaply and quickly cluster thousands of GitHub pull requests into thematic areas. This helps engineering and product leaders understand the breakdown of work between new features, tech debt, and maintenance.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.