01.Design
Author the agent
Start from a clinical or admin archetype and write the agent Skill that defines how your agent behaves, all without leaving the browser.
Medical AI benchmark toolkit
From clinical question to validated benchmark
ARISEKit is a toolkit that helps clinicians, researchers, and hospital teams design, plan, and build rigorous medical AI tools — without starting from a blank file. A clinician with an idea (“can ChatGPT tell me which of my patients need ACL repair?”) and a de-identified dataset should be able to finish with a runnable, MAST-compatible benchmark, plus the human-rater plan needed to validate it.
Three pieces of the stack, one workflow
Three pieces fit together. The model provides reasoning, the FHIR MCP layer gives the agent eyes and hands on patient data, and ARISEKit evaluates the output.
02.Tools
Connect to FHIR data
Wire MCP-style tools so your agent can read and act on patient and operational data.The catalog is pre-built for workshop speed; the patterns transfer to production.
03.Evaluation
Score before you ship
Turn rubrics, test cases, and a judge model into a quantitative eval. Know whether your agent is actually good, not just impressive in a demo.
Hands-on workshop
Enter the workshopReady to build something?
The ARISE Kit workshop walks you through the full loop in 90–120 minutes: design, tooling, eval, and take-home artifacts. No local setup required.