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

Enroll now
Skip to content

Engineering · INTERACTIVE AGENT DEMO

Robot Route Agent

Plan a delivery and adapt when the route changes.

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.

Route a supply delivery across a fictional campus grid. Compare route preferences, introduce an obstacle during execution, and inspect the moves completed within the battery limit.

Find a route and execute every move.

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, compare the shortest and quiet routes. Then add an unexpected obstacle and find how much battery the revised journey needs.

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 SIMA 2 studies agents acting toward goals in virtual environments. This navigation exercise makes the connection between planning, observed feedback, and the next action easy to inspect.

This is a working 2D pathfinding simulation with an authored controller. It does not run SIMA 2, learn from play, or control physical hardware.

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

SIMA 2: An agent that plays, reasons, and learns with you in virtual 3D worlds

SIMA 2 investigates goal-directed action and interaction across virtual 3D environments, using Gemini within an embodied agent system.

The research reports limits in long tasks, memory, visual understanding, and precise actions. Our 2D pathfinder is original deterministic code, not SIMA 2 or a physical robot.

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.