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

Enroll now
Skip to content

Student life · INTERACTIVE AGENT DEMO

Study Sprint Agent

Make a workable study plan when deadlines and free time compete.

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.

Plan four school tasks around deadlines, breaks, and a club meeting. Compare priorities, inspect the schedule, and see which work still needs time.

Room for four tasks and short breaks.

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, increase one task's estimate and inspect the change. Then add a meeting and compare both priority rules while keeping the same breaks.

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.

AWS's calendar-assistant example turns event information into validated actions. This adaptation lets you explore a related planning problem: fitting tasks into the time actually available.

Real scheduling calculations over invented tasks; an authored controller chooses the order. It reads no personal calendar and changes no account.

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.

Amazon Web Services

Build your multilingual personal calendar assistant with Amazon Bedrock and AWS Step Functions

AWS demonstrates extracting event information, validating structured actions, and executing calendar-reminder tools in a managed workflow.

Its published implementation sends reminder emails; it does not demonstrate our study scheduling algorithm. The classroom planner has no AWS or calendar connection.

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.