October workshops are openBuild a Search AI Agent$99 early bird

Enroll now
Skip to content

ENGINEERING & ENVIRONMENT · STARTER PROJECT

Lunch-waste measurement helper

Summarize a fictional cafeteria waste audit and identify measurements that need another look.

Beginner-friendly path · 8 guided lessons · editable JavaScript · runs in your browser · no API key

START WITH A QUESTION

What if a total adds grams to kilograms without converting them?

Predict how a duplicate reading or a missing unit changes an apparently precise measurement total.

Reveal what to look for

The audit normalizes permitted units, deduplicates measurement IDs, and keeps excluded readings visible with their reasons.

Start from the basicsExplore the path

8 guided lessons · learn at your pace

YOUR FINISHED BUILD

Lunch-waste measurement helper

Total valid mass, excluded row IDs with reasons, and the exact observation period.

WHY THIS FIELD USES THE IDEA

Environmental measurement depends on units, instrument status, and observation scope before interpreting an aggregate.

SEE THE IDEAChoose a step

See the idea before you code it

Read the input

Synthetic bin measurements with IDs, grams or kilograms, timestamps, and fixture scale-status fields.

function solve(input, tools) { /* your workflow */ }

Click a step to inspect this project's flow. The final workspace runs your JavaScript with original, authored records and checks.

A COMPLETE PATH TO YOUR BUILD

One small step at a time.

You can begin at the first lesson, resume shared skills you already practiced, or open the project IDE when you are ready.

01 · UNDERSTAND

Start with the essentials

No coding experience needed. These common lessons stay completed across every project.

  1. 1A model is one part of the systemFirst understand a model, a fixed workflow, and an agent that chooses its next tool call.
  2. 2Your first few lines of codeStart from zero: read values, objects, functions, and the result your code returns.
  3. 3Make a rule you can testWrite a small condition, change the input, and observe how the output changes.
  4. 4Turn an idea into a clear goalTurn the project's deliverable into a specific goal, allowed actions, and a visible stopping rule.

02 · PRACTICE

Learn the tools your project needs

Short explanations, clickable diagrams, and a small coding lab for each skill.

  1. 5A tool needs a clear contractRead the measurement value, unit, and instrument status together.
  2. 6What should the agent remember?Track processed measurement IDs so a repeated row is not counted twice.
  3. 7Return something another program can useExpose the valid total, excluded records, and observation period.

03 · BUILD

Make your project work

Follow the project-specific ideas, insert the explained snippets, and inspect your real execution trace.

  1. 8Lunch-waste measurement helperBuild and test your own version: Total valid mass, excluded row IDs with reasons, and the exact observation period.

04 · TEST & REFLECT

Try to break it. Explain what holds.

3 runnable cases check the final project. Passing them demonstrates these examples, with limitations still to explore.

Change one thing

Insert a repeated measurement ID and an unknown unit. Neither should silently increase valid mass.

Keep a useful learning record

What would you need to measure before extending this small audit to a wider environmental claim?

Open project IDEReflect & save your notes
Inputs, checks, and project boundaries
Your starting material
Synthetic bin measurements with IDs, grams or kilograms, timestamps, and fixture scale-status fields.
What your agent must check
  • Normalize units and count a repeated ID only once.
  • Exclude unreliable observations instead of treating them as zero measurements.
  • Keep the observation window exact and distinguish zero included rows.
Keep the scope clear
No real sensor control or claim about school-wide impact from a small sample. Use explicit conversion rules and fictional measurements.
Research behind this project path

Original explanations and authored practice records draw on these research and engineering ideas. The source organizations do not endorse this course or supply its fictional results.

Anthropic · Writing effective tools for agents — with agents

Design distinct tools with clear parameters, relevant returned information, and evaluations of how the agent actually uses them.

A description or schema does not guarantee the right action. A live tool can return different data for the same arguments as its environment changes.

Anthropic · Demystifying evals for AI agents

Define tasks, trials, and graders; inspect both execution records and final outcomes; repeat trials when model behavior varies.

A score depends on its cases and grading rules. Repeating a deterministic classroom case does not measure the variability of a live model.

Your JavaScript really runs. The model decisions and school data are authored simulations, so you can learn without an API key. Every workspace also includes a separate real SDK example to explore next. Passing the lab’s cases is practice, not proof that an agent is ready for real-world use.