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.

Chain Summarise and Relevance-Classify for Abstract Triage — Ai For Researchers

Day 13 · ~12 min●

extract_action_items from yesterday returns a structured list. For your systematic review inclusion step, you need a two-step chain: summarise the abstract, then classify whether it's in scope. summarize_then_classify from Day 7 used system prompts for both. What changes when the classifier uses result_type=Literal?

The summary step stays the same — Agent A with system_prompt="Summarize in 2 sentences.". The classify step replaces the system-prompt approach with result_type=Literal["in scope","out of scope","borderline"]. The Literal guarantees exactly one of those three strings.

Exactly. Agent A produces a string summary; Agent B returns a guaranteed Literal:

python

summary_agent = Agent(model, system_prompt="Summarize in 2 sentences.")
summary = summary_agent.run_sync(text).output
classify_agent = Agent(model, result_type=Literal["in scope", "out of scope", "borderline"])
return classify_agent.run_sync(summary).output

The classify agent has no system prompt. How does it know what "in scope" means without context?

Good catch. Without a system prompt, the model uses its own interpretation of the Literal labels. For a systematic review with a specific inclusion criterion, add a system prompt: "You are reviewing abstracts for a meta-analysis on early childhood interventions. Classify as in scope, out of scope, or borderline." The system prompt provides the criterion; the Literal enforces the output shape.

So the system prompt is my inclusion criterion document, and the Literal is my response format. Separated into two clean parameters.

That's the design. Criterion goes in system_prompt; allowed values go in result_type. Both are independently editable.

I could change the inclusion criterion for a different review by just changing the system prompt string. The pipeline structure doesn't change at all.

The reusable filter looks like this:

python

result = summarize_and_classify(abstract)
if result == "in scope":
    included.append(abstract)

Same pipeline, different codebook. That's reproducibility in AI-assisted research.

Summarise → Classify Chain

python

from typing import Literal

summary_agent = Agent(model, system_prompt="Summarize in 2 sentences.")
summary = summary_agent.run_sync(text).output

classify_agent = Agent(
    model,
    system_prompt="Classify relevance to early childhood intervention research.",
    result_type=Literal["in scope", "out of scope", "borderline"]
)
return classify_agent.run_sync(summary).output

Separation of concerns

system_prompt = the inclusion criterion (what counts as relevant)
result_type = the allowed output categories (what the model can return)

Make the criterion explicit

For production systematic reviews, add your inclusion criterion to the classify agent's system prompt: "You are reviewing abstracts for a meta-analysis on structured early childhood interventions aged 0-5. Classify as: in scope, out of scope, or borderline." The Literal constrains the output; the system prompt provides the scientific criterion.

Day 13 · ~12 min●

Exactly. Agent A produces a string summary; Agent B returns a guaranteed Literal:

python

summary_agent = Agent(model, system_prompt="Summarize in 2 sentences.")
summary = summary_agent.run_sync(text).output
classify_agent = Agent(model, result_type=Literal["in scope", "out of scope", "borderline"])
return classify_agent.run_sync(summary).output

The classify agent has no system prompt. How does it know what "in scope" means without context?

So the system prompt is my inclusion criterion document, and the Literal is my response format. Separated into two clean parameters.

That's the design. Criterion goes in system_prompt; allowed values go in result_type. Both are independently editable.

I could change the inclusion criterion for a different review by just changing the system prompt string. The pipeline structure doesn't change at all.

The reusable filter looks like this:

python

result = summarize_and_classify(abstract)
if result == "in scope":
    included.append(abstract)

Same pipeline, different codebook. That's reproducibility in AI-assisted research.

Summarise → Classify Chain

python

from typing import Literal

summary_agent = Agent(model, system_prompt="Summarize in 2 sentences.")
summary = summary_agent.run_sync(text).output

classify_agent = Agent(
    model,
    system_prompt="Classify relevance to early childhood intervention research.",
    result_type=Literal["in scope", "out of scope", "borderline"]
)
return classify_agent.run_sync(summary).output

Separation of concerns

system_prompt = the inclusion criterion (what counts as relevant)
result_type = the allowed output categories (what the model can return)

Make the criterion explicit

summary_agent = Agent(model, system_prompt="Summarize in 2 sentences.") summary = summary_agent.run_sync(text).output classify_agent = Agent(model, result_type=Literal["in scope", "out of scope", "borderline"]) return classify_agent.run_sync(summary).output

Summarise → Classify Chain

python

from typing import Literal

summary_agent = Agent(model, system_prompt="Summarize in 2 sentences.")
summary = summary_agent.run_sync(text).output

classify_agent = Agent(
    model,
    system_prompt="Classify relevance to early childhood intervention research.",
    result_type=Literal["in scope", "out of scope", "borderline"]
)
return classify_agent.run_sync(summary).output

Separation of concerns

system_prompt = the inclusion criterion (what counts as relevant)

result_type = the allowed output categories (what the model can return)

Make the criterion explicit

For production systematic reviews, add your inclusion criterion to the classify agent's system prompt:

"You are reviewing abstracts for a meta-analysis on structured early childhood interventions aged 0-5. Classify as: in scope, out of scope, or borderline."

The Literal constrains the output; the system prompt provides the scientific criterion.

Summarise → Classify Chain

python

from typing import Literal

summary_agent = Agent(model, system_prompt="Summarize in 2 sentences.")
summary = summary_agent.run_sync(text).output

classify_agent = Agent(
    model,
    system_prompt="Classify relevance to early childhood intervention research.",
    result_type=Literal["in scope", "out of scope", "borderline"]
)
return classify_agent.run_sync(summary).output

Separation of concerns

system_prompt = the inclusion criterion (what counts as relevant)

result_type = the allowed output categories (what the model can return)

Make the criterion explicit

For production systematic reviews, add your inclusion criterion to the classify agent's system prompt:

"You are reviewing abstracts for a meta-analysis on structured early childhood interventions aged 0-5. Classify as: in scope, out of scope, or borderline."

The Literal constrains the output; the system prompt provides the scientific criterion.

Summarise → Classify Chain

Separation of concerns

Make the criterion explicit

Summarise → Classify Chain

Separation of concerns

Make the criterion explicit

Summarise → Classify Chain

Separation of concerns

Make the criterion explicit

Sign up to practice

Summarise → Classify Chain

Separation of concerns

Make the criterion explicit

Sign up to practice