Milestone map
Milestone map
2 milestones
Do the phase's lessons in public
1–1 weeks (about 10 hrs/week, est)
Work through the 22 lessons of Phase 15: Autonomous Systems from AI Engineering from Scratch (free) and keep the autonomous systems lessons' notebooks (long-horizon agents, durable execution, cost governors, kill switches, checkpoints, safety policies) in one public repo as you go. About 12 hours (est).
Proof required
Link your public repo with the autonomous systems lessons' notebooks (long-horizon agents, durable execution, cost governors, kill switches, checkpoints, safety policies), and show your self-check (quizzes passed, notebooks run, tests passing where they exist).
What gets checked
- Each notebook runs.
- Cost limits and kill switches are shown working.
- Safety lessons are done on your own setup only.
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 the autonomous systems lessons' notebooks (long-horizon agents, durable execution, cost governors, kill switches, checkpoints, safety policies).
Steps
- Make a public repo for this phase.
- Do one lesson at a time and commit after each.
- 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.
- Write a short README: what is here and how to run it.
- Ask three people who know the topic to check it.
Template
README Phase 15: Autonomous Systems (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
- Each notebook runs.
- Cost limits and kill switches are shown working.
- Safety lessons are done on your own setup only.
- Ask about one choice in the code; the answer should be clear.
You'll sign in first, then come straight back here.
Run a long-running agent safely
2–4 weeks (6–10 hrs/week)
Use what you learned. Make a long-running agent with a cost limit, checkpoints and a kill switch, plus a written evaluation: what you tested, what failed and what you changed. It must run, be evaluated and be documented. Include a short written evaluation: what you tested, what failed and what you changed.
Proof required
Link a long-running agent with a cost limit, checkpoints and a kill switch, plus a written evaluation: what you tested, what failed and what you changed, with a README that says how to run it and what the evaluation found. Include a short written evaluation: what you tested, what failed and what you changed.
What gets checked
- The cost limit and kill switch are shown working (logs).
- It resumes from a checkpoint after a forced stop.
- The written evaluation covers what was tested, what failed and what changed.
Common mistakes
- A demo with no evaluation.
- Numbers without the data or code that produced them.
Powstik Guide
A long-running agent with a cost limit, checkpoints and a kill switch, plus a written evaluation: what you tested, what failed and what you changed.
Steps
- Write one line: what it does and for whom.
- Build the smallest version that works.
- Write the evaluation first, then improve against it.
- Write the README with the results.
- Ask three people to check it.
Template
README What it does: How to run it: How it was evaluated: Results: What was tested, what failed, what changed: 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 cost limit and kill switch are shown working (logs).
- It resumes from a checkpoint after a forced stop.
- The written evaluation covers what was tested, what failed and what changed.
- 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.