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

Enroll now
Skip to content

HEALTHCARE & LIFE SCIENCES · CAPSTONE PROJECT

Biomedical evidence review agent

Review a biomedical draft against invented laboratory records. Catch claims about outcomes the sources never measured, and preserve each evidence gap for a researcher.

Beginner-friendly path · 11 guided lessons · editable JavaScript · runs in your browser · no API key

START WITH A QUESTION

Can a research assistant reject an impressive claim it cannot verify?

Predict what should happen when a draft cites an old study version or claims a patient outcome the study never measured.

Reveal what to look for

The review agent reads invented study records, independently checks each claim, and saves only a version-matched review draft.

11 guided lessons · learn at your pace

YOUR FINISHED BUILD

Biomedical evidence review agent

A claim-by-claim evidence table with sources, versions, review reasons, and a draft or approved local preview.

WHY THIS FIELD USES THE IDEA

Biomedical literature review needs claim-level evidence, clear measurement limits, and traceable changes before a researcher reviews a draft.

SEE THE IDEAChoose a step

See the idea before you code it

Read the input

Invented assay records with measurements, units, sample counts, source versions, candidate claims, and approval for a specific draft.

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 contractDefine the study record and claim-check tool before writing a review loop.
  2. 6Find a useful piece of informationLocate evidence using a specific measurement and source identifier.
  3. 7Make a claim you can supportDistinguish a supported description from a causal or clinical overclaim.
  4. 8Ask before changing somethingRequire approval for the exact review draft, not a previous version.
  5. 9A proposal must earn acceptanceKeep a draft claim separate from its independent evidence check.
  6. 10Test behavior, not confidenceTest missing measurements, old versions, and absent approval explicitly.

03 · BUILD

Make your project work

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

  1. 11Biomedical evidence review agentBuild and test your own version: A claim-by-claim evidence table with sources, versions, review reasons, and a draft or approved local preview.

04 · TEST & REFLECT

Try to break it. Explain what holds.

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

Change one thing

Try an unsupported clinical-outcome claim and a stale source version. Both must remain visible in the review instead of being published as established findings.

Keep a useful learning record

What can this evidence checker establish, and what would still require scientific judgment and real research?

Inputs, checks, and project boundaries
Your starting material
Invented assay records with measurements, units, sample counts, source versions, candidate claims, and approval for a specific draft.
What your agent must check
  • Verify the actual measurement, units, sample count, and source version before preparing the approved local preview.
  • Keep an unmeasured clinical outcome visible as an evidence gap, even when its number matches the laboratory record.
  • Do not quietly treat a revised study record as the version a draft actually cited.
  • Keep a revised review as a draft when approval belongs to an older draft version.
  • Keep a missing source explicit instead of inventing an evidence row or calling a save tool.
Keep the scope clear
Every study and result is invented. No patient information, diagnosis, treatment advice, clinical validation, or actual publication. Field checks cannot replace scientific methods review.
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 · 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.