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.

Citations — Ai Mastery

Day 9 · ~11 min●

Yesterday's RAG answer was a paragraph. Today: the same answer with citations — [chunk-0] markers showing which sources the model used. Auditable, reproducible, and a forcing function on the model: if it can't cite, it shouldn't claim.

python

context_block = "\n".join(f"[{cid}] {entry['text']}" for cid, entry in retrieved.items())
prompt = f'''Use the context to answer the question. Cite sources as [chunk-N] in your answer.

Context:
{context_block}

Question: {query}
Answer:'''

The trick is just labeling the chunks before stuffing?

Half of it. The other half is the prompt instruction — "cite sources as [chunk-N]". With both, the model includes markers like Paris is the capital of France [chunk-0] and you can grep for them.

And we verify the citation?

Regex on the output. If \[chunk-\d+\] doesn't appear, the answer didn't cite — flag it. Production: extract the citation and check the cited chunk actually contains the claimed fact (advanced verification, beyond this lesson).

Citations — make retrieval auditable

python

def rag_with_citations(query, retrieved_items):
    # retrieved_items: list of (chunk_id, text)
    context_block = "\n".join(f"[{cid}] {text}" for cid, text in retrieved_items)
    prompt = f'''Answer the question using only the context. Cite sources as [chunk-N] inline.

Context:
{context_block}

Question: {query}
Answer:'''
    return Agent(model).run_sync(prompt).output

Two responsibilities

Label chunks before stuffing — [chunk-0] marker prefixes each chunk in the context block
Instruct the model — "cite sources as [chunk-N] inline"

Miss either, and citations don't appear.

What citations buy you

Auditability — a human (or a downstream verifier) can check the cited chunk actually supports the claim
Hallucination signal — uncited claims are more likely invented than cited ones (not always true, but a useful signal)
Trust — users see where the answer came from

Production extension — verifying citations

python

import re
cited_ids = set(re.findall(r'\[(chunk-\d+)\]', answer))
provided_ids = {cid for cid, _ in retrieved_items}
stray = cited_ids - provided_ids
if stray:
    raise ValueError(f"answer cited chunks not in context: {stray}")

This catches the failure mode "model fabricates a citation it didn't actually receive" — the regex pulls citation markers from the answer and confirms they all appeared in the retrieved chunks. Beyond this lesson, but worth knowing the pattern.

Verification in this lesson

We assert the answer contains at least one [chunk-N] marker — minimum bar for "the model is citing". Deeper checks (correct citation, claim-supports-citation) are eval-suite territory (L11).

Day 9 · ~11 min●

python

context_block = "\n".join(f"[{cid}] {entry['text']}" for cid, entry in retrieved.items())
prompt = f'''Use the context to answer the question. Cite sources as [chunk-N] in your answer.

Context:
{context_block}

Question: {query}
Answer:'''

The trick is just labeling the chunks before stuffing?

Half of it. The other half is the prompt instruction — "cite sources as [chunk-N]". With both, the model includes markers like Paris is the capital of France [chunk-0] and you can grep for them.

And we verify the citation?

Citations — make retrieval auditable

python

def rag_with_citations(query, retrieved_items):
    # retrieved_items: list of (chunk_id, text)
    context_block = "\n".join(f"[{cid}] {text}" for cid, text in retrieved_items)
    prompt = f'''Answer the question using only the context. Cite sources as [chunk-N] inline.

Context:
{context_block}

Question: {query}
Answer:'''
    return Agent(model).run_sync(prompt).output

Two responsibilities

Label chunks before stuffing — [chunk-0] marker prefixes each chunk in the context block
Instruct the model — "cite sources as [chunk-N] inline"

Miss either, and citations don't appear.

What citations buy you

Auditability — a human (or a downstream verifier) can check the cited chunk actually supports the claim
Hallucination signal — uncited claims are more likely invented than cited ones (not always true, but a useful signal)
Trust — users see where the answer came from

Production extension — verifying citations

python

import re
cited_ids = set(re.findall(r'\[(chunk-\d+)\]', answer))
provided_ids = {cid for cid, _ in retrieved_items}
stray = cited_ids - provided_ids
if stray:
    raise ValueError(f"answer cited chunks not in context: {stray}")

Verification in this lesson

We assert the answer contains at least one [chunk-N] marker — minimum bar for "the model is citing". Deeper checks (correct citation, claim-supports-citation) are eval-suite territory (L11).

Citations — make retrieval auditable

Two responsibilities

What citations buy you

Production extension — verifying citations

Verification in this lesson

Citations — make retrieval auditable

Two responsibilities

What citations buy you

Production extension — verifying citations

Verification in this lesson

Citations — make retrieval auditable

Two responsibilities

What citations buy you

Production extension — verifying citations

Verification in this lesson

Sign up to practice

Citations — make retrieval auditable

Two responsibilities

What citations buy you

Production extension — verifying citations

Verification in this lesson

Sign up to practice