Take a creative brief through drafting, revision, and review.
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.
Prepare an event headline and caption in your chosen voice. Check the event facts, revise an unsupported promise, and review the artwork permission before using the draft.
Turn a verified event brief into a draft.
Ready when you are
The tools calculate and check your inputs in an isolated JavaScript runner.
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 two voices for the same event. Then add an unsupported promise or remove asset permission and inspect the different review outcomes.
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.
The real research behind this demoWhere the idea comes from, and what this classroom version does.
Google Labs and DeepMind's Pomelli develops editable campaigns from a business profile. This adaptation combines a small creative workflow with explicit factual and asset checks for an event announcement.
The copy is assembled from original templates and fictional event records. The demo does not call Pomelli, generate images, or post to social media.
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.
Anthropic
Building effective agents
Anthropic describes tool-observation loops, bounded execution, and coding agents that use executable tests as feedback.
Our deterministic controller runs a tiny repair workflow. It is not Claude, an LLM-directed agent, or a reproduction of benchmark results.
Google Labs · Google DeepMind
Create on-brand marketing content for your business with Pomelli
Pomelli's documented creative workflow uses a business profile to suggest campaigns and produce editable branded assets.
The announcement describes a generative creative workflow, not proof of autonomous agent behavior. Our original template-based campaign draft calls no model and generates no images.
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.