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 5 · ~11 min●

"Prompt engineering" is mostly iterating, not writing the perfect prompt the first time.

Start with a vague prompt. Read what came back. Identify the specific thing that's wrong with it. Adjust the prompt to address that one thing. Re-run.

python

# v1 — vague
p = "Suggest a name for a productivity app"
# Output: "FocusFlow"  ← single name, but no rationale, no alternatives

# v2 — request structure
p = "Suggest 3 names for a productivity app, one per line"
# Output: 3 names ← better, but no rationale

# v3 — request rationale
p = "Suggest 3 names for a productivity app. For each, give a one-sentence rationale. Format: 'Name: rationale'"
# Output: 3 named pairs with reasoning

Three iterations. Each one fixes a specific gap.

When do I stop iterating?

When the output is good enough for the use case. Diminishing returns are real — past three or four iterations, you're often making it worse, not better.

The prompt-iteration loop

Write a first-pass prompt. Don't try to be perfect.
Run it. See what the model produces.
Identify ONE thing that's off. Length? Format? Tone? Missing piece?
Edit the prompt to address that one thing. Add a constraint, remove a word.
Re-run. Compare to v1 — is it closer to what you wanted?
Repeat 3-5 until good enough.

Key discipline: change ONE thing per iteration. Otherwise you can't tell which change helped.

Common gaps to fix

Gap	Fix
Output too long	"in N sentences" / "in under N words"
Output too short	"give 3 examples" / "include rationale"
Wrong format	"as a JSON object with keys X, Y"
Wrong tone	"formal" / "casual" / "as if to a child"
Missing rationale	"for each, give a one-sentence reason"
Hallucinated facts	"only use information from the text I provided"

Stopping criteria

Good enough for the task — perfect is rarely worth chasing
Past 4-5 iterations with no improvement — you've found a model limit, not a prompt problem; switch model or change approach
Output became less consistent across runs — you over-constrained; back off

Sign up to practice

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

Day 5 · ~11 min●

"Prompt engineering" is mostly iterating, not writing the perfect prompt the first time.

Start with a vague prompt. Read what came back. Identify the specific thing that's wrong with it. Adjust the prompt to address that one thing. Re-run.

python

# v1 — vague
p = "Suggest a name for a productivity app"
# Output: "FocusFlow"  ← single name, but no rationale, no alternatives

# v2 — request structure
p = "Suggest 3 names for a productivity app, one per line"
# Output: 3 names ← better, but no rationale

# v3 — request rationale
p = "Suggest 3 names for a productivity app. For each, give a one-sentence rationale. Format: 'Name: rationale'"
# Output: 3 named pairs with reasoning

Three iterations. Each one fixes a specific gap.

When do I stop iterating?

When the output is good enough for the use case. Diminishing returns are real — past three or four iterations, you're often making it worse, not better.

The prompt-iteration loop

Write a first-pass prompt. Don't try to be perfect.
Run it. See what the model produces.
Identify ONE thing that's off. Length? Format? Tone? Missing piece?
Edit the prompt to address that one thing. Add a constraint, remove a word.
Re-run. Compare to v1 — is it closer to what you wanted?
Repeat 3-5 until good enough.

Key discipline: change ONE thing per iteration. Otherwise you can't tell which change helped.

Common gaps to fix

Gap	Fix
Output too long	"in N sentences" / "in under N words"
Output too short	"give 3 examples" / "include rationale"
Wrong format	"as a JSON object with keys X, Y"
Wrong tone	"formal" / "casual" / "as if to a child"
Missing rationale	"for each, give a one-sentence reason"
Hallucinated facts	"only use information from the text I provided"

Stopping criteria

Good enough for the task — perfect is rarely worth chasing
Past 4-5 iterations with no improvement — you've found a model limit, not a prompt problem; switch model or change approach
Output became less consistent across runs — you over-constrained; back off

# v1 — vague p = "Suggest a name for a productivity app" # Output: "FocusFlow" ← single name, but no rationale, no alternatives # v2 — request structure p = "Suggest 3 names for a productivity app, one per line" # Output: 3 names ← better, but no rationale # v3 — request rationale p = "Suggest 3 names for a productivity app. For each, give a one-sentence rationale. Format: 'Name: rationale'" # Output: 3 named pairs with reasoning

The prompt-iteration loop

Write a first-pass prompt. Don't try to be perfect.

Run it. See what the model produces.

Identify ONE thing that's off. Length? Format? Tone? Missing piece?

Edit the prompt to address that one thing. Add a constraint, remove a word.

Re-run. Compare to v1 — is it closer to what you wanted?

Repeat 3-5 until good enough.

Key discipline: change ONE thing per iteration. Otherwise you can't tell which change helped.

Common gaps to fix

Gap	Fix
Output too long	"in N sentences" / "in under N words"
Output too short	"give 3 examples" / "include rationale"
Wrong format	"as a JSON object with keys X, Y"
Wrong tone	"formal" / "casual" / "as if to a child"
Missing rationale	"for each, give a one-sentence reason"
Hallucinated facts	"only use information from the text I provided"

Stopping criteria

Good enough for the task — perfect is rarely worth chasing

Past 4-5 iterations with no improvement — you've found a model limit, not a prompt problem; switch model or change approach

Output became less consistent across runs — you over-constrained; back off

The prompt-iteration loop

Write a first-pass prompt. Don't try to be perfect.

Run it. See what the model produces.

Identify ONE thing that's off. Length? Format? Tone? Missing piece?

Edit the prompt to address that one thing. Add a constraint, remove a word.

Re-run. Compare to v1 — is it closer to what you wanted?

Repeat 3-5 until good enough.

Key discipline: change ONE thing per iteration. Otherwise you can't tell which change helped.

Common gaps to fix

Gap	Fix
Output too long	"in N sentences" / "in under N words"
Output too short	"give 3 examples" / "include rationale"
Wrong format	"as a JSON object with keys X, Y"
Wrong tone	"formal" / "casual" / "as if to a child"
Missing rationale	"for each, give a one-sentence reason"
Hallucinated facts	"only use information from the text I provided"

Stopping criteria

Good enough for the task — perfect is rarely worth chasing

Past 4-5 iterations with no improvement — you've found a model limit, not a prompt problem; switch model or change approach

Output became less consistent across runs — you over-constrained; back off