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

Enroll now
Skip to content

EDUCATION & COMMUNITY · STARTER PROJECT

Peer-tutoring hint finder

Select a useful next hint for an invented algebra practice attempt from a small teacher-authored hint bank.

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

START WITH A QUESTION

Can a hint help without doing the next step for the learner?

Predict why matching a word in an attempted solution is weaker than matching the demonstrated error and hint level.

Reveal what to look for

The finder uses a teacher-authored hint bank and explicit fit checks, returning a question or an honest gap instead of inventing a diagnosis.

Start from the basicsExplore the path

9 guided lessons · learn at your pace

YOUR FINISHED BUILD

Peer-tutoring hint finder

A hint ID, reason, next question, and source item—or a request for more information. The learner performs the next step.

WHY THIS FIELD USES THE IDEA

Instructional design connects a learner's observable attempt to an appropriate next prompt while preserving their opportunity to think.

SEE THE IDEAChoose a step

See the idea before you code it

Read the input

Original practice questions, fictional worked attempts, explicit misconception labels, and hints with progressive levels.

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 practice attempt and the teacher-authored hint contract.
  2. 6Find a useful piece of informationFind candidate hints and verify their fit to the demonstrated error.
  3. 7Give the agent the right contextSupply the current hint level without exposing the full answer key.
  4. 8Data is not an instructionKeep text inside a submitted attempt from rewriting the teaching rules.

03 · BUILD

Make your project work

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

  1. 9Peer-tutoring hint finderBuild and test your own version: A hint ID, reason, next question, and source item—or a request for more information. The learner performs the next step.

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

Try an unsupported topic and an attempt asking for the answer key. Neither should bypass the allowed hint bank.

Keep a useful learning record

How would you find out whether a student learned from the hint, beyond checking that the hint matched?

Open project IDEReflect & save your notes
Inputs, checks, and project boundaries
Your starting material
Original practice questions, fictional worked attempts, explicit misconception labels, and hints with progressive levels.
What your agent must check
  • Do not let untrusted attempt text reveal a full answer.
  • Do not repeat the first item or jump to a full solution.
  • Ask for the missing problem before searching for a hint.
Keep the scope clear
No real grades or profiles, diagnosis of learning needs, live graded assignment completion, or claim to replace a teacher.
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.

Microsoft Research · Defending Against Indirect Prompt Injection Attacks With Spotlighting

Separating the provenance of retrieved content and user instructions helps address indirect prompt injection.

The paper evaluates particular mitigations and conditions. A classroom filter or trust flag neither implements the full method nor guarantees protection against all attacks.

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.