# Glass Health

**Canonical:** https://apis.io/providers/glass-health/  
**Website:** https://glass.health  
**APIs profiled:** 0

Glass Health is a San Francisco-based clinical AI company founded in 2021 by Dereck Paul (CEO) and Graham Ramsey (Head of Product) that builds an AI clinical decision support (CDS) and ambient scribing co-pilot for physicians, nurse practitioners, physician assistants, residents, and medical students. The Glass platform combines large language model reasoning with curated, physician-reviewed clinical guidelines to generate ranked differential diagnoses, evidence-based assessment and plans, chart summaries, and direct answers to clinical questions ("Consult"), all delivered with inline citations. Glass also provides ambient scribing that listens during patient encounters and generates History and Physical notes, progress notes, discharge summaries, and patient-facing instructions, plus EHR integration via SMART on FHIR to pull demographics, problem lists, medications, laboratory values, vital signs, imaging, and encounter data into the workflow. Glass offers a tiered SaaS plan (Lite free tier, Starter at $20/month, Pro at $90/month, Max at $200/month) along with iOS and Android apps, and a public Glass Developer API ($250/month minimum, token-metered beyond the floor) that exposes the same clinical AI agent — Consult, Differential Diagnosis, Assessment and Plan, and Scribing endpoints — for third-party healthcare products. Glass is backed by Breyer Capital and graduated from Y Combinator's W23 batch, with roughly $6.5M in total disclosed funding. The provider does not publish an open OpenAPI specification or open-source SDKs; integration details are gated behind the developer portal and an enterprise contact at enterprise@glass.health.

## Kin Score — 11.9 / 100 (emerging)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 11.9).

| Facet | Score |
|---|---|
| Discoverability | 50.0 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 5.3 |
| Developer Ergonomics | 9.5 |
| Commercial Clarity | 25.0 |
| Access Clarity | 25.0 |

Regulatory layer — **Health**: 13.8 (matched via tags).

## Agent readiness — 0.0 (human-only)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | no |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Unknown — onboarding: unknown, pricing: unknown, trial: no (confidence: low).

## Security (1)

- **Glass Health Domain Security** — TLSv1.3 · DMARC

## Use cases (7)

- **Triage and Differential Diagnosis** — Generating ranked differentials at the point of triage or initial workup to surface diagnoses worth considering.
- **Treatment Planning** — Producing evidence-linked treatment options and assessment-and-plan drafts for clinician review.
- **Clinical Question Answering** — Answering bedside clinical questions with citations to current medical literature.
- **Patient Record Summarization** — Synthesizing longitudinal EHR data into a coherent patient summary.
- **Ambient Documentation** — Capturing patient-clinician encounters in real time and producing structured notes without manual scribing.
- **Patient Education** — Generating plain-language discharge instructions and condition-specific handouts.
- **Medical Education** — Supporting medical students, residents, and fellows in case-based clinical reasoning practice.

## Tags

Healthcare, Clinical Decision Support, Diagnostic AI, Differential Diagnosis, Ambient Scribing, Clinical Documentation, Medical AI, Generative AI, EHR Integration, SMART on FHIR, Evidence-Based Medicine, Physician Copilot

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/glass-health/). Scores are computed from the provider's own public artifacts under a published rubric.