Iridium
Abridge writes the note.
Core trick
An evidence agent proposes billing codes, a skeptic agent tries to disprove each, and deterministic gates block codes lacking provenance before the note is revised.
Description
Abridge writes the note. ProofNote makes it safe to sign: every billing code is backed by a clickable spoken line or FHIR fact, challenged by a second agent, and resolved with the clinician before it ships.
README excerpt
# ProofNote ProofNote is the adversarial trust layer for ambient clinical notes: > Abridge writes the note. ProofNote makes it safe to sign. An Evidence Agent proposes clinical and billing candidates. A Skeptic Verifier Agent tries to disprove each one. Deterministic gates validate candidate provenance, code allowlists, policy dates, required billing context, duplicate services, and explicit diagnoses before a Grounded Revision Agent produces the final note. Every candidate code becomes one of: `SUPPORTED`, `NEEDS_CLARIFICATION`, `CONTRADICTED`, `BLOCKED_BY_RULE`, `NOT_EVALUATED`, or `WITHHELD`. The memorable behavior is that one AI can overrule another—and the system can refuse to ship a code. This repository uses only synthetic Abridge hackathon data. It is not for clinical care, coding decisions, or claim submission. ## Run it Requirements: Python 3.12 and [uv](https://docs.astral.sh/uv/). ```bash uv sync cp .env.example .env ``` Add `ANTHROPIC_API_KEY` to `.env`, load it into your shell, and start the application: ```bash set -a source .env set +a uv run uvicorn proofnote.main:app --reload ``` All agents use `claude-sonnet-5`. The model setting is exposed as `ANTHROPIC_AGENT_MODEL` but deliberately rejects other model IDs for this MVP. Configure reasoning with `ANTHROPIC_REASONING_EFFORT`; accepted values are `low`, `medium`, `high`, `xhigh`, and `max`. ## Three-minute demo 1. **Set up the problem:** select the hypertension encounter and briefly explain the