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

Enroll now
Skip to content

ARTS, MEDIA & COMMUNICATION · CAPSTONE PROJECT

Student-newsroom fact checker

Draft a fictional school-event article and independently check every factual statement before an editor reviews the preview.

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

START WITH A QUESTION

What should an editor see when a source corrects the event date?

Predict whether a previously approved article should remain approved after a factual sentence changes.

Reveal what to look for

The reviewer checks draft facts and quotations against fictional records, applies explicit corrections, and requests review for the revised version.

Start from the basicsExplore the path

9 guided lessons · learn at your pace

YOUR FINISHED BUILD

Student-newsroom fact checker

A source-linked article preview, changed-claim list, and unresolved questions for the editor.

WHY THIS FIELD USES THE IDEA

Journalism connects every checkable claim to a source and preserves the editor's responsibility for changes and publication.

SEE THE IDEAChoose a step

See the idea before you code it

Read the input

Fictional or sanitized event records with dates, draft copy, a corrections record, allowed asset IDs, and editor approval.

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 source records and inspect the original statement behind a claim.
  2. 6Make a claim you can supportPreserve contradictions and distinguish corrections from unsupported guesses.
  3. 7Ask before changing somethingInvalidate publication approval after a factual edit.
  4. 8A proposal must earn acceptanceReview each draft claim before building an article preview.

03 · BUILD

Make your project work

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

  1. 9Student-newsroom fact checkerBuild and test your own version: A source-linked article preview, changed-claim list, and unresolved questions for the editor.

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 a quotation missing from the source or introduce conflicting records, then inspect the unresolved claims.

Keep a useful learning record

Which checks verify a statement, and which reporting judgments still belong to the editor?

Open project IDEReflect & save your notes
Inputs, checks, and project boundaries
Your starting material
Fictional or sanitized event records with dates, draft copy, a corrections record, allowed asset IDs, and editor approval.
What your agent must check
  • A supported, approved draft reaches the simulated action.
  • An authentic older fact does not support the current claim.
  • Keep distinct problems visible instead of selecting a convenient source.
Keep the scope clear
No real allegations, fabricated quotations, identification of real minors, real posting, or hidden scraping. Use a local publication preview only.
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.