Milestone map
Milestone map
2 milestones
Do the phase's lessons in public
1–1 weeks (about 10 hrs/week, est)
Work through the 25 lessons of Phase 16: Multi-Agent & Swarms from AI Engineering from Scratch (free) and keep the multi-agent lessons' notebooks (supervisors, hierarchies, debate, handoffs, shared memory, consensus, failure modes) in one public repo as you go. About 14 hours (est).
Proof required
Link your public repo with the multi-agent lessons' notebooks (supervisors, hierarchies, debate, handoffs, shared memory, consensus, failure modes), and show your self-check (quizzes passed, notebooks run, tests passing where they exist).
What gets checked
- Each notebook runs.
- Each pattern is tried on the same task.
- Failures are logged, not hidden.
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 multi-agent lessons' notebooks (supervisors, hierarchies, debate, handoffs, shared memory, consensus, failure modes).
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 16: Multi-Agent & Swarms (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.
- Each pattern is tried on the same task.
- Failures are logged, not hidden.
- Ask about one choice in the code; the answer should be clear.
You'll sign in first, then come straight back here.
Compare a team of agents with one agent
2–4 weeks (6–10 hrs/week)
Use what you learned. Make a multi-agent system (a supervisor plus specialists) for a real task, compared with a single agent on the same set of at least 20 tasks. It must run, be evaluated and be documented.
Proof required
Link a multi-agent system (a supervisor plus specialists) for a real task, compared with a single agent on the same set of at least 20 tasks, with a README that says how to run it and what the evaluation found.
What gets checked
- It runs from the README.
- Both setups are scored on the same tasks, with cost shown.
- It says honestly when the team does not help.
Common mistakes
- A demo with no evaluation.
- Numbers without the data or code that produced them.
Powstik Guide
A multi-agent system (a supervisor plus specialists) for a real task, compared with a single agent on the same set of at least 20 tasks.
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: 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
- It runs from the README.
- Both setups are scored on the same tasks, with cost shown.
- It says honestly when the team does not help.
- 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.