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●

Five orchestration patterns in five days — batch triage, typed todos, Pydantic events, two-agent fan-out, and a compressed morning routine. How do these feel together?

Like layers. Typed extraction is the atom. Two agents over one input is a molecule. Compression plus fan-out is the organism — a multi-agent routine that remembers.

That is the right stack. The quiz probes the shapes — seeding counter dicts, list[PydanticModel] serialization, and when compression beats raw input.

Anything sneaky?

One question asks why the orchestrator returns the brief or memory alongside the outputs. Make sure you can articulate traceability — not just "it is neat."

Week 3 Recap

Five orchestration patterns, each composable with the others:

triage_and_count — Literal agent over a list; seeded counter dict
auto_create_tasks — result_type=list[str] plus a narrow extraction prompt
get_upcoming_events — result_type=list[Event]; .model_dump() per item
orchestrate_calendar_and_tasks — two specialists sharing one brief
morning_orchestration — summarizer into two specialists over compressed memory

Key insight: specialists plus shared state beat one overloaded agent every time.

Sign up to practice

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

Day 22 · ~11 min●

Five orchestration patterns in five days — batch triage, typed todos, Pydantic events, two-agent fan-out, and a compressed morning routine. How do these feel together?

Like layers. Typed extraction is the atom. Two agents over one input is a molecule. Compression plus fan-out is the organism — a multi-agent routine that remembers.

That is the right stack. The quiz probes the shapes — seeding counter dicts, list[PydanticModel] serialization, and when compression beats raw input.

Anything sneaky?

One question asks why the orchestrator returns the brief or memory alongside the outputs. Make sure you can articulate traceability — not just "it is neat."

Week 3 Recap

Five orchestration patterns, each composable with the others:

triage_and_count — Literal agent over a list; seeded counter dict
auto_create_tasks — result_type=list[str] plus a narrow extraction prompt
get_upcoming_events — result_type=list[Event]; .model_dump() per item
orchestrate_calendar_and_tasks — two specialists sharing one brief
morning_orchestration — summarizer into two specialists over compressed memory

Key insight: specialists plus shared state beat one overloaded agent every time.

Week 3 Recap

Five orchestration patterns, each composable with the others:

triage_and_count — Literal agent over a list; seeded counter dict

auto_create_tasks — result_type=list[str] plus a narrow extraction prompt

get_upcoming_events — result_type=list[Event]; .model_dump() per item

orchestrate_calendar_and_tasks — two specialists sharing one brief

morning_orchestration — summarizer into two specialists over compressed memory

Key insight: specialists plus shared state beat one overloaded agent every time.

Week 3 Recap

Five orchestration patterns, each composable with the others:

triage_and_count — Literal agent over a list; seeded counter dict

auto_create_tasks — result_type=list[str] plus a narrow extraction prompt

get_upcoming_events — result_type=list[Event]; .model_dump() per item

orchestrate_calendar_and_tasks — two specialists sharing one brief

morning_orchestration — summarizer into two specialists over compressed memory

Key insight: specialists plus shared state beat one overloaded agent every time.