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 6 · ~11 min●

Four task verbs cover ~80% of practical LLM use: summarize, infer, transform, expand. The next four lessons walk through each.

First: summarize. Take longer text, produce shorter text that retains the meaning.

python

long_text = "Python is a high-level, general-purpose programming language. ... (200 words)"
prompt = f"Summarize this in one sentence:\n\n{long_text}"
result = Agent(model).run_sync(prompt)
print(result.output)

Just "summarize this"?

Plus the constraint — "in one sentence". Without it the model picks an arbitrary length. Specify what you want.

Summarize — reduce text

The canonical pattern:

python

result = Agent(model).run_sync(
    f"Summarize the following in one sentence:\n\n{long_text}"
)

Key design choices:

Length constraint — "in one sentence", "in 50 words", "in 3 bullet points". Without it, the output length is arbitrary.
Audience hint — "for a beginner", "for an executive summary". Shapes vocabulary and depth.
Format — "as a numbered list", "as a single paragraph".

Where summarize shines

Long-form articles → 3-bullet TL;DR
Meeting transcripts → action items
Customer emails → one-line intent
Chat history → status update

Limitations

Hallucinated detail — the model might add facts that weren't in the source. Mitigation: "only use information from the text I provided".
Lost specifics — short summaries drop numbers, names, exact phrasing. If those matter, ask for them explicitly: "include any numbers or dates in the summary".
Context window — very long texts (book-length) won't fit in one prompt. Chunking + iterative summarize is the pattern; AI Advanced covers it.

Sign up to practice

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

Day 6 · ~11 min●

Four task verbs cover ~80% of practical LLM use: summarize, infer, transform, expand. The next four lessons walk through each.

First: summarize. Take longer text, produce shorter text that retains the meaning.

python

long_text = "Python is a high-level, general-purpose programming language. ... (200 words)"
prompt = f"Summarize this in one sentence:\n\n{long_text}"
result = Agent(model).run_sync(prompt)
print(result.output)

Just "summarize this"?

Plus the constraint — "in one sentence". Without it the model picks an arbitrary length. Specify what you want.

Summarize — reduce text

The canonical pattern:

python

result = Agent(model).run_sync(
    f"Summarize the following in one sentence:\n\n{long_text}"
)

Key design choices:

Length constraint — "in one sentence", "in 50 words", "in 3 bullet points". Without it, the output length is arbitrary.
Audience hint — "for a beginner", "for an executive summary". Shapes vocabulary and depth.
Format — "as a numbered list", "as a single paragraph".

Where summarize shines

Long-form articles → 3-bullet TL;DR
Meeting transcripts → action items
Customer emails → one-line intent
Chat history → status update

Limitations

Hallucinated detail — the model might add facts that weren't in the source. Mitigation: "only use information from the text I provided".
Lost specifics — short summaries drop numbers, names, exact phrasing. If those matter, ask for them explicitly: "include any numbers or dates in the summary".
Context window — very long texts (book-length) won't fit in one prompt. Chunking + iterative summarize is the pattern; AI Advanced covers it.