Skip to content
Live nowSeason 1 ยท Episode 5 ยท GPS
AI

Week One

Generates a personalized onboarding checklist by diffing your skills against the repo. Built for Pair Programmer's Apprentice โ€” use lumen forge to build a tool for developers who are new to a codebase. Checklist generation and progress tracking. The interface is deliberately narrow: one path, done properly, rather than a broad surface that half-works at the deadline.

Sofia MarchettiSubmitted โ€”50.5/ 100
๐Ÿ”ฅ 29๐Ÿš€ 16๐Ÿคฏ 1

Gallery

Screens

Week One โ€” main view

Week One โ€” result state

On the clock

What shipped, what didn't

Completed in time

Checklist generation and progress tracking.

Unfinished / faked

Skills come from a manual form, not your commit history.

Obstacles

The first approach needed a background worker I didn't have time to deploy, so I moved it inline at minute 14.

Lessons learned

Writing the submission summary first would have caught the scope problem earlier.

Process

Prompting approach

Started from a single system prompt describing the user and their constraint, then iterated with the assistant on the Week One data model before writing any interface code. Full prompt log is in the repository under /prompts.

Fairness

Disclosures

Declared by the builder at submission time, visible to judges before scoring.

Pre-existing code reusedDisclosed

Reused a personal utility file for date formatting (~40 lines), linked in the repo README.

Template or boilerplate usedNone
CollaboratorsSolo
Work before the build windowNone

Judging

Public feedback

Judges' private notes stay private โ€” this is what they chose to say publicly.

Elena Voss

VP of Engineering, Harbor Compute

The idea is strong and the execution is most of the way there. The demo path broke once, which is what separates this from the top three today.

Marcus Bell

Founder, Bellwether Studio

Solid build with a clear user in mind. The interface is doing less than it could โ€” a second pass on hierarchy would lift this considerably.

Hana Kobayashi

Principal Research Engineer, Independent

Good instinct on the problem. I would have liked to see the model doing more of the reasoning rather than formatting output.

Discussion

0 comments

No comments yet.

Week One ยท ๐Ÿ•๏ธ AI