{"id":109532,"title":"Hubble: Retrieve medical records other APIs can't","tagline":"Your user verifies their identity once, and we return their medical records through one API.","body":"**TL;DR:** Hubble gives your product a patient's medical records through a single API. Your user verifies their identity once, and we assemble their records from across the providers they've seen and return them for your AI agent to use. Where APIs are not sufficient, we keep going with AI (browser and voice agents). Every request runs on the patient's individual right of access.\n\n**The problem**\\\nIf you're building something that needs a patient's records, there's no clean way to get them. A patient's history is scattered across every provider they've ever seen, and each system is its own island. Most APIs returns the patient-portal subset rather than the full record, and coverage is inconsistent because every health system sets up its integration differently. So most teams either build per-provider integrations for months, fall back to faxes and manual portal logins, or push the problem back onto the patient by asking them to track down their own records or remember a login they set up years ago and have long since lost.\n\n**What Hubble does**\\\nYour user verifies their identity once, and we go get their records so you don't have to.\n\n* **One verification, no work on your end.** The patient verifies their identity in a couple clicks. After that, assembling the records is our job, not yours and not theirs.\n* **We don't stop at the portal subset.** We connect into EHRs and HIEs where they work, and when an API comes back empty we keep going.\n* **Browser and voice agents for everything else.** Agents submit the patient's request through provider portals and call records departments on the patient's behalf, working the phone trees so nobody on your team has to.\n* **Built on the patient's right of access.** Every request runs on the patient's individual right of access. They review every source we request from and can revoke at any time. Every retrieval is logged.\n\n**About the team**\\\nWe're the team behind the AI agents at Grow Therapy and Amazon's One Medical, used by millions of patients. Prabha was Grow's first PM building and scaling their AI agents. Aaron built the AI infrastructure at One Medical serving 1M+ clients. (Fun fact: we've known each other for over a decade.)\n\n**Our ask**\n\n* If your product needs patient records, reach out and we'll get you access: [prabha@hubble.ai](mailto:prabha@hubble.ai)\n* Intros to anyone building AI products on patient data, in digital health, care delivery, life sciences, or legal tech.\n\nSign up at [hubble.ai](http://hubble.ai)\n\n\u003chttps://www.youtube.com/watch?v=TC9QoaFHlRk\u003e","slug":"SUe-hubble-retrieve-medical-records-other-apis-can-t","created_at":"2026-08-10T16:00:00.087Z","updated_at":"2026-09-19T01:21:09.858Z","total_vote_count":20,"url":"https://www.ycombinator.com/launches/SUe-hubble-retrieve-medical-records-other-apis-can-t","share_image_url":"//bookface-static.ycombinator.com/assets/ycdc/yc-og-image-c440a0ad1dacfb86eeeb343717479cc54d256614449b4ef719977a0a451f8bc8.png","company":{"id":33062,"name":"Hubble","slug":"hubble-ai","url":"https://hubble.ai/","logo":"https://bookface-images.s3.amazonaws.com/small_logos/8d58ef930283a4163ee9544b3936abd1327a463a.png","batch":"Summer 2026","industry":"Healthcare","tags":["B2B","Healthcare"],"search_path":"https://bookface.ycombinator.com/company/33062"}}