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

Enroll now
Skip to content

Healthcare · INTERACTIVE AGENT DEMO

Biomedical Evidence Desk

Find the research lead that survives a closer look at its controls.

Change the briefRun working toolsInspect the result

YOUR TURN TO EXPERIMENT

Free to explore · No sign-in or API key

Give the agent a brief.

Review two synthetic bench-assay study cards. Compare each candidate with its matched control, inspect repeated measurements, and prepare a source-backed note for a researcher.

A has the higher raw reading. See why B can still be the stronger research lead in this fixture.

Working local tools. Authored controller and classroom data. No live AI model or external action.

A SMALL BRIEF. A VISIBLE RESULT.

See the agent at work.

Start with a scenario, change a detail, and run the demo. Your result and the steps behind it will appear here.

1 · Read the brief2 · Use tools3 · Check the result

Try this twistRaise candidate B's control until the two mean differences tie. Then introduce variable readings and explain why the review status changes even when the mean stays the same.

Open the code behind this agentRead it, change it, run your own variation.

This is the JavaScript that powers the demo. agent.js coordinates the workflow; tools.js contains its available tools. Tool calls and returned data are inspectable after each run.

Ready when you are

⌘ / Ctrl + Enter runs your agent.js draft with the current inputs. Tab leaves the editor. Package imports and network calls are unavailable in this bounded environment.

Ready for a real model and open-source tools? Explore the separate local SDK setup

The real research behind this demoWhere the idea comes from, and what this classroom version does.

Google DeepMind's Co-Scientist develops and critiques research hypotheses using literature and data before researcher review. This original exercise focuses on one part of that workflow: deciding what measured evidence can support.

All candidates, assay readings, units, and study cards are invented. Real JavaScript computes the comparisons, but no medical finding, live model, patient data, or treatment advice is involved.

STEMtiq authored this exercise. The named organizations do not endorse it. The JavaScript tools run locally; the controller is programmed, and classroom records are labeled examples. This is not a live instance or reproduction of the referenced research system.

Google DeepMind

Co-Scientist: A multi-agent AI partner to accelerate research

Co-Scientist proposes, critiques, and refines research hypotheses using scientific literature and data, with proposals reviewed by researchers.

Our evidence board adapts source inspection and checking. It neither runs Co-Scientist nor generates or validates medical findings. All classroom assay cards and measurements are invented.

Where will your curiosity go next?

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.