patrickz
Before you start
A coding agent, browser and an empty practice repository.
Why this lesson exists
The original JRPG-inspired personal operating system kept one Today view instead of ten dashboards, and it added cloud sync and AI only after the manual quest loop worked.
Do the exercise
Set your boundary
Keep the first version to task creation, completion and a short review. Use invented tasks and no health or account data.
Define a Quest type
Define a Quest type with title, status, effort and due date.
Save quests locally
Save quests locally and build create and complete actions. A completed quest must stay completed after a reload.
Add one Today view
Add one Today view instead of ten dashboards.
Add an evening review
Add an evening review that compares intention with outcome, using only the quests you stored.
Next sessions, not today
- Archive Add an archive action once create and complete survive a reload.
- Morning question Add a morning question: “What would make today count?”
- Cloud sync and AI Add cloud sync and AI only after the manual loop works.
A prompt to adapt
Replace the bracketed parts with your own details.
Help me build a local-first daily quest planner in [plain TypeScript or the framework you know] in a new practice folder. First version only: create and complete quests, one Today view and a short evening review, with invented quests. Store quests locally only: no accounts, cloud sync or AI API, and no archive or morning question yet. List the setup commands before changing any files. Then work in four checkpoints and, after each, tell me how to check it: 1. TypeScript domain types for a Quest with title, status, effort and due date. 2. A small repository interface backed by IndexedDB, with create and complete, so a completed quest stays completed after a reload. 3. One Today view instead of ten dashboards. 4. An evening review that compares planned with completed quests, using only stored records. My invented quests: [three short tasks].
Once it runs, paste your code and ask:
Review this Today view for cognitive overload. Rank every visible element by whether it helps me choose the next action, and recommend what to hide, combine or delay.
Run this experiment
Add two quests, complete one, reload and inspect the Today view. The evening summary must distinguish planned from completed work using those records.
Check your result
Use evidence from your output. A confident explanation from the AI is not enough.
If it isn’t working
If a dashboard grows before task persistence works, pause new screens and fix the create-complete-reload loop.
Optional. Progress stays in this browser.
Where this came from
Public project repository ↗. The practice lesson is an adaptation, not a verbatim transcript. About the sources.
Prepared September 2026. Tools and interfaces change; use current official setup instructions. Session lengths are estimates.