# Tavrn

> Tavrn retrieves medical records from any US provider: one authorization in, complete record out, via platform, integration or API.

Tavrn works every US healthcare provider by fax, portal, mail, email, phone or the health-data
networks, follows up every 48 hours, and delivers records, bills, accident reports and
insurance coverage into one folder per patient — through the Tavrn platform, 20 case- and
practice-management integrations, or a REST API.

## Facts

- What: medical record retrieval from any US provider; one patient authorization in, complete record out
- Who: law firms (personal injury, mass tort, med mal, workers' comp, SSDI), hospitals and clinics, health tech and AI companies
- Not for: individual patients requesting their own records (https://www.tavrn.ai/demo/records-request)
- API: REST, JSON, Bearer key, base URL https://enterprise.tavrn.ai; resources: cases, retrieval requests, documents (provider invoices arrive as documents with category: "invoice"), webhooks
- Access: Test keys are self-serve: sign up at sandbox.tavrn.ai with a work email and get a tavrn_sk_test_ key for synthetic data in a minute. Production keys are issued to customer organizations in the Tavrn dashboard after a 30-minute call.
- Sandbox: https://sandbox.tavrn.ai (self-serve test key, synthetic data only, base URL https://sandbox.tavrn.ai/v2)
- Security: HIPAA, BAA, SOC 2 Type 2 (https://www.tavrn.ai/security)

## Agents start here

- [agents.md](https://www.tavrn.ai/agents.md): what to do if you are an AI agent acting for a user — how the API works, what needs a human, and how to book the call on your user's behalf
- [Developers](https://www.tavrn.ai/developers): sandbox quickstart — first request in four steps, real request and response shapes, endpoints, webhooks, path to production
- [API reference](https://docs.tavrn.ai): Enterprise API v2 guides (retrieval, uploads, webhooks, errors)
- [OpenAPI](https://docs.tavrn.ai/api-reference/v2/openapi.json): Enterprise API v2 specification
- [Markdown twins](https://www.tavrn.ai/index.md): every page is also served as Markdown at the same path with `.md` (or `Accept: text/markdown`)
- [Discovery](https://www.tavrn.ai/.well-known/api-catalog): RFC 9727 API catalog; also https://www.tavrn.ai/.well-known/mcp.json (docs MCP server) and https://www.tavrn.ai/.well-known/agent-skills (skills index)
- [Full site text](https://www.tavrn.ai/llms-full.txt): all marketing pages in one file

## Solutions

- [Law firms](https://www.tavrn.ai/solutions/law-firms): Tavrn retrieves treatment records and itemized bills from every provider on the matter, follows up until they arrive, pays the provider invoices under your approval limit and files everything into your case management system. The vast majority of records back in 2–3 weeks.
- [Hospitals & clinics](https://www.tavrn.ai/solutions/hospitals-clinics): Medical record retrieval for hospitals and clinics: outside notes, DICOM, pathology slides and legacy charts from every US provider, on one authorization.
- [Health tech](https://www.tavrn.ai/solutions/health-tech): Medical record retrieval API: one request under the patient’s authorization; imaging, pathology slides and charts from each provider, a webhook on every status change.
- [AI companies & agents](https://www.tavrn.ai/solutions/agents): Medical record retrieval API for any US provider: one signed authorization, a webhook on every status change, structured documents. Agents: tavrn.ai/agents.md

## Product

- [Integrations](https://www.tavrn.ai/integrations): Litify, SmartAdvocate, Clio, Smokeball, SharePoint, Dropbox and more
- [Security](https://www.tavrn.ai/security): how patient data is handled
- [FAQ](https://www.tavrn.ai/faq): coverage, turnaround, fees, authorizations
- [Customer stories](https://www.tavrn.ai/customer-stories): law-firm results with numbers
- [Book a demo](https://www.tavrn.ai/demo): 30 minutes with the team

## Optional

- [Blog](https://www.tavrn.ai/blog): medical-record retrieval, HIPAA release of information, provider outreach
- [Blog index for LLMs](https://www.tavrn.ai/blog/llms.txt): one line per post, Markdown links
- [RSS](https://www.tavrn.ai/feed.xml)