Prove
LiveProof-of-Work · Oct–Nov: every verified proof counts. 35 days leftAll outcomes
Skills

Learn Capstone Projects (AI Engineering Phase 19)

8 weeks · 2 milestones

Phase 19 of AI Engineering from Scratch: 85 free lessons, then one project of your own that is run, evaluated and documented. Part of the Varsity Curriculum: AI Engineering.

Milestone map

Milestone map

2 milestones

Do the phase's lessons in public

3–5 weeks (about 10 hrs/week, est)

Work through the 85 lessons of Phase 19: Capstone Projects from AI Engineering from Scratch (free) and keep one of the phase's capstone tracks (for example the coding-agent harness, the production RAG chatbot or the GPT-from-scratch series), built end to end in one public repo as you go. About 48 hours (est).

Proof required

Link your public repo with one of the phase's capstone tracks (for example the coding-agent harness, the production RAG chatbot or the GPT-from-scratch series), built end to end, and show your self-check (quizzes passed, notebooks run, tests passing where they exist).

What gets checked

  • The track's tests pass where it has them; otherwise its demo runs as described.
  • Each lesson's quiz in the track is passed.
  • The repo shows the work step by step (history).

Common mistakes

  • Copying the repo's solutions: verifiers read your history and ask about your code.
  • Skipping the self-check, then asking for review too early.

Powstik Guide

A public repo with one of the phase's capstone tracks (for example the coding-agent harness, the production RAG chatbot or the GPT-from-scratch series), built end to end.

Steps

  1. Make a public repo for this phase.
  2. Do one lesson at a time and commit after each.
  3. Self-check: Run each lesson's code; it must work on your machine as the lesson shows. Run each lesson's notebook top to bottom; its outputs must match the lesson. Each lesson has a quiz (quiz.json, also on the course site): pass it. Some capstone lessons ship tests: they must pass.
  4. Write a short README: what is here and how to run it.
  5. Ask three people who know the topic to check it.

Template

README
Phase 19: Capstone Projects (AI Engineering from Scratch)
What is here:
How to run it:
Self-check result:
What was hardest:

What gets sent back

  • One big upload with no history.
  • Self-check not shown.
  • Code that does not run from the README.

Resources

Foundationstart here

Depthgo deeper

What a verifier looks for

  • The track's tests pass where it has them; otherwise its demo runs as described.
  • Each lesson's quiz in the track is passed.
  • The repo shows the work step by step (history).
  • Ask about one choice in the code; the answer should be clear.

You'll sign in first, then come straight back here.

Extend a capstone project

2–4 weeks (6–10 hrs/week)

Use what you learned. Make one feature of your own added to the capstone project you built, with an evaluation that shows it helps. It must run, be evaluated and be documented.

Proof required

Link one feature of your own added to the capstone project you built, with an evaluation that shows it helps, with a README that says how to run it and what the evaluation found.

What gets checked

  • The feature works from the README.
  • Before-and-after evaluation numbers are shown.
  • Limits are stated honestly.

Common mistakes

  • A demo with no evaluation.
  • Numbers without the data or code that produced them.

Powstik Guide

One feature of your own added to the capstone project you built, with an evaluation that shows it helps.

Steps

  1. Write one line: what it does and for whom.
  2. Build the smallest version that works.
  3. Write the evaluation first, then improve against it.
  4. Write the README with the results.
  5. Ask three people to check it.

Template

README
What it does:
How to run it:
How it was evaluated:
Results:
Limits:

What gets sent back

  • Does not run from the README.
  • No evaluation.
  • Claims more than the evaluation shows.

Resources

Foundationstart here

What a verifier looks for

  • The feature works from the README.
  • Before-and-after evaluation numbers are shown.
  • Limits are stated honestly.
  • Run it, or watch it run: it must work, be evaluated and be documented.
  • Check that the work is the person's own.

You'll sign in first, then come straight back here.