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

Enroll now
Skip to content

Psychology · INTERACTIVE AGENT DEMO

Survey Insight Agent

Turn survey responses into a finding you can explain and qualify.

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.

Analyze an editable club survey, calculate preference shares and response rate, and assess a proposed conclusion against the question wording and collection method.

Find the shares and response rate.

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 twistFirst, change the invitation count while keeping votes fixed. Then compare neutral and leading wording and explain what the calculator cannot resolve.

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 Research's DS-STAR connects data inspection, executable analysis, and verification. This adaptation applies those steps to a social-research question with visible counts and explicit limits.

The arithmetic and checks run on invented aggregate counts. This is not psychological assessment, a population study, or a DS-STAR integration.

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 Research

DS-STAR: A state-of-the-art versatile data science agent

DS-STAR inspects data files, plans analyses, executes code, and revises its plan using a verifier's feedback.

Its verifier is model-based and fallible. Our small aggregate survey calculator does not run DS-STAR, reproduce benchmark scores, or establish facts about real students.

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.