Trace a proposed contract action to the right clause and review record.
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 a fictional service agreement. Find the clause that applies on the request date, check a proposed termination-notice period, and prepare a briefing with an explicit review trail.
Trace a 30-day proposal to its applicable clause and matching review.
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 twistKeep 14 days of notice and move the request from November to October. Then remove the review record or ask for the missing liability clause and compare the reasons for pausing.
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.
Anthropic's Harvey case study describes contract analysis and guided legal document workflows with human review checkpoints. This original adaptation makes source applicability, exact passages, and scoped review visible.
Every contract clause, date, notice period, and reviewer record is invented. The program checks explicit fixture rules; it provides no legal advice, sends no notice, and uses no legal AI service.
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 · Harvey customer case study
Harvey transforms legal work with Claude
The customer case study describes guided legal document workflows with intermediate work and human review checkpoints.
This is a vendor-published case study, not independent proof of legal accuracy. Our fictional contract exercise provides no legal advice and uses neither Harvey nor Claude.
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.