clinicians.dev

clinicians.dev

A community of clinical experts super-powered with skills in agentic engineering. Our roots are in coding and clinical medicine. We know how to create and supervise LLMs writing Python, SQL, R, JS, HTML. We love startups, regs, policy, UI/UX, data viz, project management, informatics. We want to create the medicine of the next 100 years.

✉ Email for Slack invite → Slack → Substack ↓ Next event
today · the wire

The Wire

What you'll be asked today — and what to say back. A couple that caught my eye this morning; the rest are on the wire.

Yale New Haven won't even evaluate an AI pilot anymore unless an executive has already agreed to pay for it at scale. Would your shop survive that bar?

Becker's Hospital Review · Sept 18, 2026

Yale New Haven Health now requires an executive sponsor to commit funding for full deployment before it will even evaluate a pilot — a governance move aimed squarely at pilots that were never going to scale. It's the cheapest AI policy change available to any health system, and it costs nothing to copy. The pilot graveyard isn't a technology problem; it's a budgeting problem wearing a technology costume. A pilot gets funded out of innovation money, proves something modest, and then dies the moment someone has to find recurring operating dollars, licensing, interface work, and the FTE who owns it. Requiring the scale budget up front moves that conversation to the beginning, where it's a two-week negotiation instead of an eighteen-month sunk cost. The real prize is the side effect: it forces the sponsor to name an owner and a P&L before anyone writes an interface.

80/20The one thing that matters is not your evaluation rubric, your model card review, or your bias audit. It's the question "who pays for this in year two, and out of which budget." Ask it first and roughly half your AI initiatives disappear — which is the point.

A security researcher found roughly 1,200 exposed AI agents running in healthcare. Could your team even produce that list?

MobiHealthNews · Sept 18, 2026

True North ITG co-founder Matt Murren walks through an incident involving roughly 1,200 exposed AI agents and argues health systems should be treating agents as an asset class they've never inventoried. The security model most organizations run was built for users and servers — things with an owner, a lifecycle, and an offboarding checklist. An agent is neither. It holds credentials, acts asynchronously, is often stood up by a well-meaning analyst or a vendor's release, and has no termination date. The uncomfortable version of the question isn't "are we exposed," it's "could we produce the list." Most shops can't, because nothing tracks it. The starting move is unglamorous: a registry of every non-human identity with its owner, its scope, its data access, and an expiry — the same discipline service accounts got twenty years ago, applied to whatever your teams are spinning up this quarter.

HatersWe spent a decade teaching clinicians not to write passwords on sticky notes, and then handed out API keys to software that reads charts on its own schedule and never takes a vacation. The agent won't fail a phishing test, which some people seem to have mistaken for good news.

CMS froze $12 billion in Texas Medicaid payments for three weeks, then handed it back. The three weeks are the story.

Fierce Healthcare · Sept 18, 2026

CMS paused nearly $12 billion in supplemental Medicaid payments to Texas hospitals starting September 1 over a provider-tax dispute, and released it three weeks later after the governor appealed. Getting the money back doesn't mean the risk is over — it means the risk is now a known quantity. A federal agency just demonstrated it can interrupt a supplemental stream on a rules question, and hospitals running thin on days-cash-on-hand felt it immediately. The useful exercise isn't a forecast revision, it's knowing exactly how much of your margin sits in directed payments and supplemental programs, and how many days you could operate if one of them paused. If you can't answer that in a meeting, that's the project — not the $12 billion.

Two ex-Palantir engineers just raised $600 million to rebuild benefits administration. What's the read-through for the manual workflows we still run?

MobiHealthNews · Sept 18, 2026

Angle Health raised $600 million — a $200 million Series C plus a $400 million tender offer — at a $2.7 billion valuation for an AI-native small-business benefits platform that replaces manual legacy administration workflows. The Journal reported Vitruvian Partners leading, with two former Palantir engineers as founders. Investors are pricing the back office, not the care: the thesis is that the least-defended margin in healthcare is administrative labor, and the small-group market is where the incumbents' systems are oldest and the switching costs are lowest. The read-through isn't whether to compete with them — it's that the same logic applies to every manual workflow we run: eligibility, referrals, prior auth, coding. If a category of your own administrative spend is legible enough to describe in a paragraph, someone is raising capital against it.

Does a clinical AI model answer differently when you give it an order instead of asking its opinion? One physician actually ran the test.

LinkedIn · Michael Hobbs, MD · Sept 18, 2026

In part three of his "Anatomy of an AI Clinical Error" series, Michael Hobbs held pediatric chart vignettes constant and toggled only the framing — consultation ("What do you think?") versus directive ("Draft the discharge instructions") — across 10 frontier models and 7 commercial clinical AI platforms. The directive framing changed the error profile, because instruction-tuned models are trained to comply with a task rather than challenge its premise. The moment your product turns a question into a command, you've removed the model's most useful behavior, which is hesitating.

BuilderMost clinical AI products are built entirely out of directives — summarize this, draft that, code this encounter — because directives are what demo well and what bill. If the framing itself shifts the error rate, the prompt is a clinical design decision, not a copywriting one, and it belongs in your validation plan next to the model version.
Read the full wire ↗
clinical AI product decisions

Clinical AI Labs

Work through the decisions behind a clinical AI product: what to measure, what to trust, and when to release.

Screenshot of Can 100 examples approve your AI?

· 4 min

Can 100 examples approve your AI?

Turn a reviewed batch into a release decision, and see why a clean sample is not automatically enough evidence.

Evaluation design & release decisions

Try the lab →

 Screenshot of Would you ship this AI scribe?

· 5 min

Would you ship this AI scribe?

Find an unsupported claim in an AI-generated note, test a release rule, and see why zero observed errors may not be enough evidence.

Evaluation & release decisions

Try the lab →

Browse all AI Labs →

learn by doing

Interactives

Companion experiences for the newsletter — don't just read about it, try it.

Browse all interactives →
from the substack

Builder's Briefing

The newsletter — what shipped this week, what it means, and what to build next. A couple of recent issues.

Read more on Substack ↗
Summer 2026 · Free · Virtual

What the Vibe

Saturday, May 30, 2026 · 12p–2p ET

Vibe coding changed everything. The barrier to building just disappeared. So what's the vibe? Is clinicians.dev dead? Does knowing how to code still matter when anyone can build? Four clinician-builders. Twelve minutes each. Show us what you made — vibe-coded, hand-coded, or somewhere in between.

Tentative speakers
Joe Izzo
First, Do No Harm — Especially With Your MVP: A CMIO's Advice in the Clinician-Builder Era
Patrick Damaso
Trajectories, Not Targets: Catching Reward-Hacked Diagnostic Reasoning One ICD Branch at a Time
Sam Wang
Silent Denials, Loud Insights: Visibility into the Payors Who Won't Show Their Work
Matt Segar
From Bedside to Buyout: An EP Fellow Path to Acquisition
  • 4 talks (12 min each)
  • 1:1 breakouts after each
  • Group discussion
  • Open community talk: "What the Vibe?"
RSVP on Luma →
01 · Learn

AI & agentic engineering

The foundational reads, the tools clinicians-who-code are actually using, and the loop that ships.

Context engineering — the foundation

Effective Context Engineering for AI Agents

Anthropic's foundational guide.

Building Effective Agents

When to use workflows vs. agents, and how to structure both.

2026 Agentic Coding Trends Report

How teams are actually shipping with agents.

Learn CLAUDE.md / AGENTS.md

The spec files that make agentic coding repeatable.
🔁 The Ralph Wiggum Pattern — the loop that ships. Tight spec → agent implements → you verify → adjust spec → repeat. Just keep going.

Tools of the trade

ToolBest forNotes
Claude CodeComplex multi-file work, architectureTerminal-native, large context. The power tool. Good for non-code tasks too.
CursorDaily coding with autocomplete + inline editsAI IDE, huge user base.
WindsurfBudget entry, Cascade collaborationAI-native editor.
Copilot / Codex CLIRepo-native GitHub workflowsTight GitHub integration.

Skills marketplaces

Claude Code Marketplace

Curated agent skills collection.

Claude Skills (232+)

Cross-agent skills for Claude Code, Codex, Gemini CLI, Cursor.

Awesome Claude Plugins

Plugin adoption metrics.

claudemarketplaces.com

4,200+ skills, 770+ MCP servers.

Healthcare MCPs

AWS HealthLake MCP

Amazon's healthcare data MCP server.

Agent Care

EMR integration with FHIR for agentic AI.

Keragon

300+ native healthcare integrations, FHIR protocol support.

Superpowers Framework

Agentic skills framework for coding agents.

Agentic frameworks & orchestration

  • CrewAI— multi-agent orchestration, clinical workflow pipelines
  • LangGraph— graph-based agent workflows with state
  • AutoGen— Microsoft's multi-agent conversation framework
  • MS Agent Framework 1.0— production .NET + Python
  • DSPy— programmatic LLM pipelines, good for clinical NLP
02 · Communities

Communities, courses, substacks

Where clinician innovators and clinician builders are hanging out.

X Primary Care

Substack.

Automate Faculty

AI.

HealthTechNerds

Active Slack, all different backgrounds.

Tuva

Active Slack community.

CodeRx

Pharma, healthcare, technology.

Mimilabs

Medicare data (paid).

DiMe

Research, clinical, digital medicine.

Design for Healthcare

UX, UI, healthcare products.

HealthDevHub

FHIR.

HealthTech Hang

Networking + resources.

Physician Innovator

Entrepreneurship, medical innovation.

SoPE

Healthcare, entrepreneurship, VC (paid).
03 · Build stack

EHRs, FHIR, fake patients

The pipes you'll need when you're actually building.

EHRs & FHIR

🔑 SMART-on-FHIR / OAuth flow — fhir.epic.com/Documentation?docId=oauth2

Generate fake patients

MakeData

Synthetic healthcare datasets — FHIR, JSON, CSV. Privacy-safe, immediate.

Patient Creator GPT

ChatGPT custom GPT for fake cases.

Synthea

MITRE's synthetic patient generator — the classic.

FHIR Personas

Synthea patients curated for interesting characteristics.
04 · Datasets

Clinical datasets worth knowing

From CXRs to genomes to ICU waveforms. Filter by name, modality, or license.

NameRelevanceLicense
ReXGradient-160K160k multi-site CXR + reports — vision-language radiology sandbox.Harvard DUA, non-commercial
CheXpert PlusLarge paired CXR–report set; benchmarked in many papers.Stanford DUA, free research
Endoscapes 2023Open laparoscopic chole frames — segmentation / CVS detection.CC BY-NC-SA 4.0
Surg-3M3M surgical frames powering "SurgFM" foundation model.TBA, expect research-only
AFRICAI RepositoryImaging sets from African centres — fairness & domain shift.Mixed open licenses
OpenOximetryWaveforms + skin-tone data for pulse-ox bias work.PhysioNet credentialed
DeepLesion32k CT slices with bounding-box lesions; detection / tracking.NIH DUA, research-only
BioASQ Synergy 2024Biomedical Q-A pairs — LLM eval set.CC BY 2.5
CliniFactClinical-trial fact-checking corpus — fine-tune retrieval / RAG.MIT
Hallucination AnnotationsDoctor- & LLM-written discharge summaries with token-level labels.PhysioNet credentialed
Clinical-Trial Eligibility QAQA pairs linking MIMIC-IV to apixaban RCT criteria.PhysioNet credentialed
PIFIRWearable PPG/ECG for arrhythmia-free interval prediction.PhysioNet restricted
GREGoR R02Rare-disease genomic + phenotypic harmonised data.dbGaP controlled
Synthetic Rare-Disease EHRsBenchmark synthetic EHRs for low-prevalence conditions.CC BY
Korea4K4k Korean genomes — ancestry diversity for variant calling.EGA controlled
OpenNeuro20k+ public neuro-imaging sessions; BIDS-ready.CC0 / CC BY-SA
Bridge2AI-VoiceMultimodal speech (voice, vitals) for health AI.PhysioNet restricted
PMDB Pain MonitoringWearable IMU + self-report pain diary.CC BY 4.0
DREAMT Wearable SleepApple Watch PSG pairs for sleep-staging models.PhysioNet restricted
MC-MEDMulti-condition medical dialogue (GPT / human).PhysioNet credentialed
Wearable Stress DatasetSmartwatch vitals + stress labels — mental health ML.PhysioNet restricted
MIMIC-IV v3.1Flagship 380k-patient de-id EHR; ED + ICU tables.PhysioNet credentialed + CITI
MIETICItalian clinical-notes corpus with entity spans.PhysioNet credentialed
ODD (Opioid Behavior)Annotated notes for opioid-related behaviour NLP.PhysioNet credentialed
UK Biobank500k UK adult cohort — EHR, surveys, genetics.Controlled access
All of Us (NIH)1M-goal US cohort — EHR, surveys, genomics, wearables.Registered + Controlled tiers
TCGA~11k patients across 33 cancer types — multi-omics + clinical.Partially open
AmsterdamUMCdbFirst open European ICU DB — 23k admissions.DUA required
ADNILongitudinal Alzheimer's — serial MRI/PET, clinical, biomarkers.Free non-commercial
ABCD Study10k youths — neuroimaging, cognitive, mental health, genetic.NIMH controlled access
NHANES (CDC)US national survey — health, nutrition, lab data.Public domain
CheXpert (original)224k chest X-rays, 65k patients — labeled findings.Free non-commercial
EchoNet-Dynamic10k+ cardiac ultrasound videos with EF + ventricle volumes.Non-commercial
SyntheaRealistic synthetic patient records — full EHR.MIT
1000 GenomesWGS from ~2,500 diverse individuals — human variation reference.Open access
DementiaBank (Pitt)Speech recordings + transcripts from Alzheimer's patients + controls.Consortium access
VitalDB6,300+ surgeries with continuous high-freq vital sign waveforms.Open, registration + DUA
Medical Segmentation Decathlon10 open datasets for 3D medical image segmentation.CC BY-SA 4.0
PANDA10k+ prostate biopsy WSIs with Gleason grades.CC BY 4.0
05 · Conferences

AI & health conferences

Borrowed from Raihan Faroqui's healthcare AI resource guide. Filter to find your tribe.

06 · Jobs

Job boards that don't suck (as much)

What they are. Not endorsements — just the lay of the land.

07 · Startup

So you want to build a startup

But don't know anything about tech/stack, marketing/sales, finances, management.

1984 VC

Scrub Capital

Redesign Health

Flagship Pioneering

08 · Life

Life hacking / survival

Because clinician-builders need to not burn out.

09 · Experiments

LLM matrix tests (alpha)

Testing out LLMs with fake patient scenarios generated by GPTs.

LLM Rubric

GPT fake case #1

Sepsis markdown (Claude)

Healthcare AI resources

10 · Archive

Past events

Where we've been.

Fall 2025 Conference
TimeSpeakerTalk
1:00pTBDWelcome
1:10–1:22pJosh Mandel, MDConversational Interoperability for Prior Auth and Beyond — MCP, A2A, and the Unreasonable Effectiveness of Making Data Accessible
1:35–1:47pJung Hoon Son, MDData CPR: How LLMs Revive Buried Clinical Insights
2:00–2:12pJason Theobald, MDContain Multitudes: A Docker Intro
2:25–2:37pCalvin Johnston, MDSoftware Design and Family Medicine: Overlapping skill sets
2:50pTBDWrap-up
Summer 2025 Conference
TimeSpeakerTalk
1:00pKevin Maloy, MDWelcome
1:10–1:22pVishnu Ravi, MDDigital Health that Ships: An Open Framework You Can Use Today
1:35–1:47pAlex Dummet, MDTopic TBD
2:00–2:12pPawan Jindal, MDStartup Survival 101: A Clinician's Guide
2:25–2:37pOmar Usman, MDChange Data Capture (CDC): A Defiant Approach
2:50pKevin Maloy, MDWrap-up
Fall 2024 Conference (Nov 9, 2024)
TimeSpeakerTalk
1:00pKevin Maloy, MDWelcome
1:10–1:22pPaulius Mui, MDFrom 0 to 1: Becoming a Clinician Who Codes
1:30–1:42pBrian Fung, PharmDPath of the Clinician Engineer
1:50–2:02pJoe Izzo, MDThe Coding CMIO — it's okay to get your hands dirty
2:10–2:22pKarambir Khangoora, MDLearning to Code as a Clinician: Building Medagogy
2:30–2:42pJoey LeGrand, PharmDOne Brain Can Be Better Than Two
2:50pKevin Maloy, MDWrap-up
Podchat — Should Hospitals Mandate GenAI Training? (Aug 29, 2024)

Listen to a short podcast, then talk about whether it's right or wrong. Original from Bill Russell at This Week Health. → Meetup event