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 9 · ~11 min●

Third task verb: transform. Take text and produce different text with the same meaning — translation, rephrasing, reformatting.

python

result = Agent(model).run_sync("Translate to Spanish: 'Hello, how are you today?'")
print(result.output)
# something like: "Hola, ¿cómo estás hoy?"

LLMs are excellent at transform. It's a pure language task with abundant training data — every English-to-Spanish parallel corpus contributed to the weights.

Transform — change shape, preserve meaning

The pattern: input text + transformation directive.

python

result = Agent(model).run_sync(f"{directive}: {text}")

Common transformations

Directive	Example
Translate to X	`"Translate to Spanish: ..."`
Rewrite as formal	`"Rewrite this email more formally: ..."`
Convert to bullets	`"Convert this paragraph to a bulleted list: ..."`
Tone shift	`"Rewrite this in a casual tone: ..."`
Genre shift	`"Rewrite this technical doc as if for a 10-year-old: ..."`

Where transform shines

Translation — high-quality across major languages
Tone/register shifts — formal ↔ casual, terse ↔ verbose
Format conversions — paragraph ↔ bullets ↔ table
Audience adaptation — same content, different reading level

Where transform stumbles

Code translation — high-level language → high-level language often works (Python ↔ JavaScript). Edge cases (asyncio, language-specific idioms) get bungled.
Lossless conversion — "convert this CSV to JSON" works for simple cases; for complex schemas you want code, not LLM.
Strict format — the model mostly respects format, occasionally slips. Validate the output if format matters.

Sign up to practice

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

Day 9 · ~11 min●

Third task verb: transform. Take text and produce different text with the same meaning — translation, rephrasing, reformatting.

python

result = Agent(model).run_sync("Translate to Spanish: 'Hello, how are you today?'")
print(result.output)
# something like: "Hola, ¿cómo estás hoy?"

LLMs are excellent at transform. It's a pure language task with abundant training data — every English-to-Spanish parallel corpus contributed to the weights.

Transform — change shape, preserve meaning

The pattern: input text + transformation directive.

python

result = Agent(model).run_sync(f"{directive}: {text}")

Common transformations

Directive	Example
Translate to X	`"Translate to Spanish: ..."`
Rewrite as formal	`"Rewrite this email more formally: ..."`
Convert to bullets	`"Convert this paragraph to a bulleted list: ..."`
Tone shift	`"Rewrite this in a casual tone: ..."`
Genre shift	`"Rewrite this technical doc as if for a 10-year-old: ..."`

Where transform shines

Translation — high-quality across major languages
Tone/register shifts — formal ↔ casual, terse ↔ verbose
Format conversions — paragraph ↔ bullets ↔ table
Audience adaptation — same content, different reading level

Where transform stumbles

Code translation — high-level language → high-level language often works (Python ↔ JavaScript). Edge cases (asyncio, language-specific idioms) get bungled.
Lossless conversion — "convert this CSV to JSON" works for simple cases; for complex schemas you want code, not LLM.
Strict format — the model mostly respects format, occasionally slips. Validate the output if format matters.