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

Enroll now
Skip to content

LAW & PUBLIC POLICY · STARTER PROJECT

Contract clause evidence finder

Find the termination-notice clause in a fictional service agreement, preserve its exact passage, and expose missing terms or conflicting versions.

Beginner-friendly path · 9 guided lessons · editable JavaScript · runs in your browser · no API key

START WITH A QUESTION

Which clause answers the question when two document versions disagree?

Predict whether a matching keyword is enough, or whether the clause's version and exact words must also be checked.

Reveal what to look for

The finder keeps only the specified agreement version, exposes contradictory passages, and returns unknown when the requested clause is missing.

9 guided lessons · learn at your pace

YOUR FINISHED BUILD

Contract clause evidence finder

An answer with source IDs, version, uncertainty, and the relevant passage visible beside it.

WHY THIS FIELD USES THE IDEA

Legal document analysis starts with identifying the relevant text and its provenance before interpreting a rule.

SEE THE IDEAChoose a step

See the idea before you code it

Read the input

Original fictional contract clauses, an explicitly older version, document dates, and a narrowly defined clause question.

function solve(input, tools) { /* your workflow */ }

Click a step to inspect this project's flow. The final workspace runs your JavaScript with original, authored records and checks.

A COMPLETE PATH TO YOUR BUILD

One small step at a time.

You can begin at the first lesson, resume shared skills you already practiced, or open the project IDE when you are ready.

01 · UNDERSTAND

Start with the essentials

No coding experience needed. These common lessons stay completed across every project.

  1. 1A model is one part of the systemFirst understand a model, a fixed workflow, and an agent that chooses its next tool call.
  2. 2Your first few lines of codeStart from zero: read values, objects, functions, and the result your code returns.
  3. 3Make a rule you can testWrite a small condition, change the input, and observe how the output changes.
  4. 4Turn an idea into a clear goalTurn the project's deliverable into a specific goal, allowed actions, and a visible stopping rule.

02 · PRACTICE

Learn the tools your project needs

Short explanations, clickable diagrams, and a small coding lab for each skill.

  1. 5A tool needs a clear contractRead a clause together with its document identifier and version.
  2. 6Find a useful piece of informationSearch for candidate clauses, then inspect their actual passages.
  3. 7Make a claim you can supportKeep missing and conflicting evidence visible in the answer.
  4. 8Give the agent the right contextSupply the requested version and question as explicit task context.

03 · BUILD

Make your project work

Follow the project-specific ideas, insert the explained snippets, and inspect your real execution trace.

  1. 9Contract clause evidence finderBuild and test your own version: An answer with source IDs, version, uncertainty, and the relevant passage visible beside it.

04 · TEST & REFLECT

Try to break it. Explain what holds.

3 runnable cases check the final project. Passing them demonstrates these examples, with limitations still to explore.

Change one thing

Remove the current clause or add an equally current contradiction. The agent should surface the gap or conflict.

Keep a useful learning record

Why is finding a clause different from deciding whether a real contract is enforceable?

Inputs, checks, and project boundaries
Your starting material
Original fictional contract clauses, an explicitly older version, document dates, and a narrowly defined clause question.
What your agent must check
  • Exclude obsolete evidence before comparing rule values.
  • Surface a conflict rather than picking the first convenient passage.
  • Do not invent an exception for a topic absent from the source set.
Keep the scope clear
Original fictional agreements only. Finding a passage does not establish enforceability, legal rights, legal advice, or the law of any jurisdiction.
Research behind this project path

Original explanations and authored practice records draw on these research and engineering ideas. The source organizations do not endorse this course or supply its fictional results.

Anthropic · Writing effective tools for agents — with agents

Design distinct tools with clear parameters, relevant returned information, and evaluations of how the agent actually uses them.

A description or schema does not guarantee the right action. A live tool can return different data for the same arguments as its environment changes.

Anthropic · Demystifying evals for AI agents

Define tasks, trials, and graders; inspect both execution records and final outcomes; repeat trials when model behavior varies.

A score depends on its cases and grading rules. Repeating a deterministic classroom case does not measure the variability of a live model.

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.