---
title: "Health & science AI agents · clinical and research agents · Agent Fieldbook"
url: https://agentfieldbook.org/catalog/health_science/
description: "Health and science agents for evidence-driven, high-stakes work: ambient clinical scribing and documentation, and research agents that hypothesise, synthesise literature and analyse results. Accuracy, auditability and oversight over fluency, each specced against primary sources."
section: "Catalogue · Health & Science"
source: Agent Fieldbook — generated from the published page
---

# Health & science agents

Clinical and research agents for evidence-driven, high-stakes work: ambient scribing and clinical documentation on one side, hypothesis generation and literature synthesis on the other. Both demand accuracy, auditability and expert oversight over fluency, because the output has to be checkable against a source. Click a card for its full spec.

## 9 agents Live data · click a specimen for its anatomy

## Field notes

Evidence-driven domains where output must be checkable

Health and science agents split cleanly by whether a regulator is involved. Research and literature tools move quickly; anything touching diagnosis, triage or a patient record moves at the pace of clinical validation.

The interesting work sits on the research side, where an agent can read more of the literature than any individual and propose candidates for a human to test. That is a genuine expansion of capacity rather than a substitution of labour, and it is where the category is compounding fastest.

- [Brandon Chaplin](https://www.linkedin.com/in/brandon-chaplin-digital-marketing-strategist)

## Common questions

### What is an AI medical scribe?

A tool that listens to a consultation and drafts the clinical note from it, so the clinician edits rather than types. Ambient scribing is the most widely deployed clinical use of AI agents, because the risk is contained: a human reads and signs the note.

### Can AI diagnose patients?

Not on its own in normal practice. Software intended to inform a diagnosis is regulated as a medical device in most countries, which means clinical evidence and approval before it can be used. Most deployed tools stay on the documentation side of that line deliberately.

### Is patient data safe with an AI scribe?

It depends on the vendor and the contract. Recordings and notes are protected health data, so check where audio is stored, how long it is kept and whether it is used for training. In the US the vendor must sign a HIPAA business associate agreement before handling that data.

### Can AI agents do scientific research?

They can do parts of it: searching and summarising literature, proposing hypotheses, writing analysis code and running simulations. They cannot run the experiment, and any result still has to reproduce. Current systems produce candidates for people to test, not findings to trust.

## Next in the learning path

- [Vertical SaaS agents The broader pattern these verticals sit inside](https://agentfieldbook.org/catalog/vertical_saas/)

- [Safety evals How high-stakes agents get tested](https://agentfieldbook.org/security/evals/)

- [Human oversight Why clinical work stays human-in-the-loop](https://agentfieldbook.org/security/oversight/)

- [Retrieval patterns How research agents ground their claims](https://agentfieldbook.org/memory/retrieval/)

## Entries

_9 entries listed on this page._

| name | description | subjectOf |
| --- | --- | --- |
| Hippocratic AI | Patient-facing healthcare agents for scheduling, intake, outreach and chronic-care: built safety-first for non-diagnostic tasks. | https://www.hippocraticai.com |
| OpenEvidence | Evidence-based clinical question-answering for physicians: one of the most valuable healthcare AI companies. | https://www.openevidence.com |
| Abridge | Ambient clinical documentation, listens to the visit and drafts the note inside the EHR. | https://www.abridge.com |
| Ambience Healthcare | Ambient documentation + Chart Chat copilot embedded directly in Epic for context-aware clinical insight. | https://www.ambiencehealthcare.com |
| Nabla | Ambient clinical documentation with fast deployment and a clean workflow, used widely outside the US-only market. | https://www.nabla.com |
| FutureHouse (Robin / Kosmos) | Multi-agent AI scientists that generate hypotheses, design experiments and analyze data: Robin identified ripasudil as a candidate therapy autonomously. | https://www.futurehouse.org/about |
| Sakana AI Scientist | Automates the research lifecycle via agentic tree search: produces workshop-level papers end-to-end. | https://github.com/SakanaAI/AI-Scientist-v2 |
| Lila Sciences | Building AI that performs the scientific method autonomously at superhuman speed: "scientific superintelligence". | https://www.lila.ai/ |
| Consensus AI | AI-powered search engine over 200M+ research papers: evidence-based answers with citations. | https://consensus.app/ |