How much does zuzu.codes cost?

The starter track is free — read all lessons and practice for free. Full access to every track (current and future) is $14.99/month. Cancel anytime.

How long does each track take?

Each track is designed as a 30-day challenge — one lesson per day, about 15 minutes each. Go at your own pace, but the structure is built around daily consistency.

What's the lesson format?

Each lesson is a student-teacher dialogue with code examples, followed by a hands-on code challenge in an in-browser editor. You read, you understand, then you write real code.

Do I need prior coding experience?

Our beginner track starts from absolute zero — no prior experience needed. Advanced tracks build on earlier ones, and the platform tells you exactly where to start.

How is zuzu.codes different from freeCodeCamp or Codecademy?

zuzu.codes uses a structured 30-day track format with dialogue-based teaching, an in-browser code editor, and gamification (XP, streaks, progress tracking). The format builds genuine understanding through daily practice.

Day 22 · ~11 min●

Agents and evals — the heart of the track. Ten questions, 80% to pass.

When you pass, week 4 ramps to production patterns: typed outputs, retry-on-bad-output extended, multi-step planning chains, and a capstone with real Composio.

What week 3 covered

Lesson	Concept
15	What's an agent? — LLM + tools + loop, terminator = no more tool calls
16	Agent loop in code — pydantic-AI's `Agent` runs the loop, `result.all_messages()` to inspect
17	Multi-tool agent — 3 tools, model picks per task
18	Eval suite — (input, expected) pairs, pass-rate threshold
19	Iteration via evals — change one thing, re-score, attribute the win
20	Synthesis — agent + 2 tools + 3-case eval, ≥ 2/3 pass

Week 4: typed outputs, retry-on-bad-output extended, scoring rubrics, multi-step planning chains, agent + Composio, final integration synthesis.

Sign up to practice

Create a free account to get started. Paid plans unlock all tracks.

Day 22 · ~11 min●

Agents and evals — the heart of the track. Ten questions, 80% to pass.

When you pass, week 4 ramps to production patterns: typed outputs, retry-on-bad-output extended, multi-step planning chains, and a capstone with real Composio.

What week 3 covered

Lesson	Concept
15	What's an agent? — LLM + tools + loop, terminator = no more tool calls
16	Agent loop in code — pydantic-AI's `Agent` runs the loop, `result.all_messages()` to inspect
17	Multi-tool agent — 3 tools, model picks per task
18	Eval suite — (input, expected) pairs, pass-rate threshold
19	Iteration via evals — change one thing, re-score, attribute the win
20	Synthesis — agent + 2 tools + 3-case eval, ≥ 2/3 pass

Week 4: typed outputs, retry-on-bad-output extended, scoring rubrics, multi-step planning chains, agent + Composio, final integration synthesis.

What week 3 covered

Lesson	Concept
15	What's an agent? — LLM + tools + loop, terminator = no more tool calls
16	Agent loop in code — pydantic-AI's `Agent` runs the loop, `result.all_messages()` to inspect
17	Multi-tool agent — 3 tools, model picks per task
18	Eval suite — (input, expected) pairs, pass-rate threshold
19	Iteration via evals — change one thing, re-score, attribute the win
20	Synthesis — agent + 2 tools + 3-case eval, ≥ 2/3 pass

Week 4: typed outputs, retry-on-bad-output extended, scoring rubrics, multi-step planning chains, agent + Composio, final integration synthesis.

What week 3 covered

Lesson	Concept
15	What's an agent? — LLM + tools + loop, terminator = no more tool calls
16	Agent loop in code — pydantic-AI's `Agent` runs the loop, `result.all_messages()` to inspect
17	Multi-tool agent — 3 tools, model picks per task
18	Eval suite — (input, expected) pairs, pass-rate threshold
19	Iteration via evals — change one thing, re-score, attribute the win
20	Synthesis — agent + 2 tools + 3-case eval, ≥ 2/3 pass

Week 4: typed outputs, retry-on-bad-output extended, scoring rubrics, multi-step planning chains, agent + Composio, final integration synthesis.