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

Enroll now
Skip to content

EVERYDAY PRACTICE · CAPSTONE PROJECT

School-week coordination agent

Coordinate a fictional week of homework, club meetings, a team project, and an event deadline. Review every proposed calendar change.

Beginner-friendly path · 10 guided lessons · editable JavaScript · runs in your browser · no API key

START WITH A QUESTION

What happens when a calendar changes after a plan was approved?

Predict whether yesterday's approval can authorize a newly changed schedule, then inspect the version checks.

Reveal what to look for

A refreshed observation changes the proposed plan. The save preview must match the specific plan version a person reviewed.

Start from the basicsExplore the path

10 guided lessons · learn at your pace

YOUR FINISHED BUILD

School-week coordination agent

A calendar preview, unresolved conflicts, changed-input notes, and a review point before a simulated save.

WHY THIS FIELD USES THE IDEA

Everyday practice: coordinate changing tasks while keeping uncertainty and personal control visible.

SEE THE IDEAChoose a step

See the idea before you code it

Read the input

Synthetic tasks and events, availability, priorities, a versioned calendar snapshot, changed-event cases, and approval for a specific plan version.

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 contractTreat calendar reads and preview saves as different capabilities.
  2. 6What should the agent remember?Retain a calendar version so a stale observation can be identified.
  3. 7Ask before changing somethingBind approval to the actual proposed schedule.
  4. 8Fail clearly and recover carefullyStop repeated refresh failures without inventing current availability.
  5. 9A proposal must earn acceptanceCheck the whole proposal before accepting it.

03 · BUILD

Make your project work

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

  1. 10School-week coordination agentBuild and test your own version: A calendar preview, unresolved conflicts, changed-input notes, and a review point before a simulated save.

04 · TEST & REFLECT

Try to break it. Explain what holds.

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

Change one thing

Move an event after approval, then verify that the updated plan requires a new review.

Keep a useful learning record

Which parts can be recalculated automatically, and which change needs another person's decision?

Open project IDEReflect & save your notes
Inputs, checks, and project boundaries
Your starting material
Synthetic tasks and events, availability, priorities, a versioned calendar snapshot, changed-event cases, and approval for a specific plan version.
What your agent must check
  • A matching approval permits a checked preview.
  • Replan after one retry, then invalidate approval for the old interval.
  • Stop with the last verified version and no fabricated current plan.
  • Reject the mismatched version before planning.
Keep the scope clear
Use fictional records only. No actual accounts, messages, calendar changes, or invented permission from classmates. A preview is not a confirmed arrangement.
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 · Building effective agents

Distinguish fixed workflows from model-directed actions; start simply, use tool observations as feedback, and set stopping conditions.

The article notes that its tooling landscape has changed. Its patterns do not establish that a more autonomous or complex system is better for every task.

OpenAI · Guardrails and human review

Distinguish automatic checks from approval decisions, pause sensitive tool requests, retain state, and resume after an application approves or rejects them.

Model-generated approval text is not authorization. Resume examples that automatically approve a request do not establish that a person reviewed it.

Amazon Builders’ Library · Marc Brooker · Timeouts, retries, and backoff with jitter

Handle transient failures with timeouts and bounded retries, consider backoff and jitter, and establish whether repeating an operation is safe.

Retries can amplify overload or duplicate side effects. Three immediate classroom attempts are an exercise rule, not a universal policy for real services.

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.