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

Enroll now
Skip to content

PSYCHOLOGY & SOCIAL SCIENCES · CAPSTONE PROJECT

Study-app experiment auditor

Compare two invented study-app trials and identify conclusions needing revision before a science-club presentation.

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

START WITH A QUESTION

Did the study app help, or did the groups start differently?

Predict why a higher final score alone cannot settle whether an intervention caused an improvement.

Reveal what to look for

The auditor reads invented assignment methods, baselines, and dropout information before accepting the scope of a draft conclusion.

Start from the basicsExplore the path

9 guided lessons · learn at your pace

YOUR FINISHED BUILD

Study-app experiment auditor

A claim audit separating supported observations, missing information, and remaining explanations.

WHY THIS FIELD USES THE IDEA

Behavioral research compares study designs and alternative explanations; a polished conclusion cannot repair missing methodological information.

SEE THE IDEAChoose a step

See the idea before you code it

Read the input

Invented trial records with assignment method, pre/post scores, sample sizes, dropouts, and an overstated draft conclusion.

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 trial's methods and measurements, not just its headline result.
  2. 6Make a claim you can supportSeparate measured differences from causal conclusions.
  3. 7Test behavior, not confidenceDesign a counterexample with unequal starting conditions.
  4. 8A proposal must earn acceptanceAudit each proposed conclusion against the original trial record.

03 · BUILD

Make your project work

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

  1. 9Study-app experiment auditorBuild and test your own version: A claim audit separating supported observations, missing information, and remaining explanations.

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

Compare equal final scores with different starting scores, then remove dropout information and inspect the review gaps.

Keep a useful learning record

Which alternative explanation remains possible after your checks, and how would you investigate it?

Open project IDEReflect & save your notes
Inputs, checks, and project boundaries
Your starting material
Invented trial records with assignment method, pre/post scores, sample sizes, dropouts, and an overstated draft conclusion.
What your agent must check
  • Keep a fully documented fixture descriptive without certifying causation.
  • Expose a post-only mistake, self-selection, an invented sample size, and a causal overclaim.
  • Retain an unreported dropout count as an unresolved method question.
Keep the scope clear
Label every trial as invented. No claims about real app effectiveness, real grades, diagnoses, judgments of student ability, or universal product recommendations.
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.

NIH · Understanding Clinical Studies

Observational associations and randomized intervention designs support different kinds of conclusions.

This explains study design; it does not provide evidence for the fictional study cards in this lab. Direct page access was blocked during review; its primary indexed text was available.

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.