Overview
What this challenge is about.
Design a ReAct prompt with tool-call loops for legal research, then score accuracy and citation F1 to earn a verifiable certificate.
The scenario
The consultancy (12 staff) bills by the bespoke engagement and needs a defensible eval to justify a USD 80K build to a 40-attorney boutique firm.
The Brief
What you'll do, and what you'll demonstrate.
Design a ReAct-style legal-research agent that calls 4 tools in correct sequence and produces a cited memo a paralegal would accept.
Earning criteria — what you'll demonstrate
- Design a ReAct prompt with clean tool-call schemas
- Build an agent loop that handles tool errors and dead-ends
- Evaluate agent quality on multiple axes (correctness, citation, readability)
- Document failure modes for product iteration
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Aligned coursework coming soon.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- React Prompting
Apply react prompting to solve real industry problems and demonstrate production-level capability.
- Tool Use
Apply tool use to solve real industry problems and demonstrate production-level capability.
- Agent Design
Apply agent design to solve real industry problems and demonstrate production-level capability.
- Json Schema
Apply json schema to solve real industry problems and demonstrate production-level capability.
- Evaluation
Apply evaluation to solve real industry problems and demonstrate production-level capability.
- Citation Handling
Apply citation handling to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
AI Engineer
Building a tool-using ReAct agent with a real eval suite is the day-one skillset for AI engineer roles at any vertical AI startup.
This challenge sharpens
- react-prompting
- tool-use
- agent-design
Prompt Engineer
Designing the ReAct system prompt and tool schemas under accuracy + readability targets is core prompt-engineer territory.
This challenge sharpens
- react-prompting
- json-schema
- evaluation
NLP Engineer
Citation handling and document-grounded generation are bread-and-butter NLP-engineer work at legal-tech companies.
This challenge sharpens
- citation-handling
- tool-use
- evaluation