The Second Read
An ambient AI scribe treats the doctor-patient conversation as ground truth and writes it down.
Core trick
Runs a citation-grounded Claude pass over the draft note against nursing and therapy records, dropping any finding whose quote fails code verification.
Description
An ambient AI scribe treats the doctor-patient conversation as ground truth and writes it down. The Second Read is the verification layer that reads the note back against the rest of the chart before it is signed.
The target market is post-acute care and skilled nursing, where documentation drives both PDPM reimbursement, discharge safety, and continued patient care. The tool lives inside the sign note action itself. A single citation-grounded Claude pass reconciles the draft against every PT, nursing, OT, and consult note the physician might have missed. Each contradicted sentence is flagged with verbatim, timestamped evidence, alongside a drafted correction that the physician approves or dismisses one flag at a time.
Three properties make it safe to trust:
1. No quote, no finding. Every citation is re-verified in code against its source document. A finding that cannot produce its supporting quote is dropped before the physician ever sees it.
2. Silence over false alarms. It understands that CMS Section GG tasks are clinically distinct, so a difference in scoring across tasks is not treated as a contradiction.
3.It flags in both directions. When the physician is right and the chart is stale, it flags the record, not the physician.
The scribe heard one conversation in one room. The Second Read reads everything else: the nurse at 10pm, the therapist at 2pm, and the buried consult note. That is where the patient's real story might be hidden.
README excerpt
# The Second Read **Every ambient AI scribe treats the doctor's words as truth and writes them down. The Second Read is the agent that reads the note back against the rest of the chart — and challenges the doctor's own input when the nursing, therapy, pharmacy, or dietitian record says the patient has changed.** Built for the Abridge Hackathon. Target setting: **post-acute care / skilled nursing facilities (SNFs)**, where documentation *is* reimbursement (PDPM) and stale, contradictory charts cause both denied claims and patient harm. ## Why it matters In a SNF, the **Section GG functional lines** the physician signs map directly to the **PDPM PT/OT case-mix groups that set the daily rate** — so a functional claim that contradicts therapy's own coding is at once a reimbursement error *and* an audit/denial trigger, because payers reconcile the signed note against the same interdisciplinary record this agent reads. And when the *chart* is the stale one — a MAR that hasn't caught up to a new anticoagulation order — the gap is **missed doses and stroke risk**. The Second Read catches both, at the one moment a human is already looking: **the signature**. ## What it does The Second Read is **embedded in the "Sign note" action**. When the clinician signs an ambient-generated (or pasted) note, the agent reconciles it against the rest of the chart *before the signature commits* — a single citation-grounded pass that reasons in five steps: 1. **Retrieve** — the full interdiscipl