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

Enroll now
Skip to content

BUSINESS, MARKETING & FINANCE · CAPSTONE PROJECT

School-club campaign reviewer

Prepare a factual event announcement and spending plan, then verify its claims and pause for review.

Beginner-friendly path · 9 guided lessons · editable JavaScript · runs in your browser · no API key

START WITH A QUESTION

Can a campaign be persuasive without inventing its facts?

Predict which checks a convincing announcement still needs: event details, spending, asset rules, and approval.

Reveal what to look for

The reviewer compares the authored campaign's claims with event records and blocks unsupported statements before a local preview.

Start from the basicsExplore the path

9 guided lessons · learn at your pace

YOUR FINISHED BUILD

School-club campaign reviewer

An announcement preview, exact cost, claim-to-source checklist, and required edits.

WHY THIS FIELD USES THE IDEA

Marketing operations combines factual messaging, asset permissions, budget control, and editorial review.

SEE THE IDEAChoose a step

See the idea before you code it

Read the input

Fictional event facts, permitted asset IDs, fixture channel costs, a spending limit, draft copy, and approval for that draft 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 contractSeparate fact reads, cost calculation, and preview publication.
  2. 6Make a claim you can supportTrace announcement claims to the supplied event facts.
  3. 7Ask before changing somethingKeep publication tied to the exact approved campaign version.
  4. 8A proposal must earn acceptanceCheck a proposed message and spending plan before accepting them.

03 · BUILD

Make your project work

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

  1. 9School-club campaign reviewerBuild and test your own version: An announcement preview, exact cost, claim-to-source checklist, and required edits.

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

Add an unsupported donation claim or use approval for a different draft, then inspect the blocked preview.

Keep a useful learning record

Which creative choices can vary freely, and which factual claims need an exact source?

Open project IDEReflect & save your notes
Inputs, checks, and project boundaries
Your starting material
Fictional event facts, permitted asset IDs, fixture channel costs, a spending limit, draft copy, and approval for that draft version.
What your agent must check
  • A fully checked exact version reaches only the simulated action.
  • Approval cannot make a false or unsupported claim pass factual review.
  • Version mismatch stops publication even when the facts and costs fit.
Keep the scope clear
No real ads, payments, guaranteed returns, personal targeting, or student profiling. Asset usage follows explicit rules of the exercise.
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.

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.

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.