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.

Epic opened the connector layer. Did it also hand you the liability?

John Lee, MD · Aug 26, 2026

Agent Factory lets your organization configure and activate MCP connectors yourself. That sounds like openness. It is also the moment the integration risk moves from Epic's ledger to yours. The read from the UGM usability lab is that Epic built an application layer on top of a data core that did not move — Chronicles, Clarity and Caboodle are as closed today as before Agent Factory shipped. What opened is the connector tier, and the configuration step is the transfer point. When your team activates a connector, your team owns what it does, what it reads, and what it sends. Epic used to hold that. There's a second-order effect too: every third party visibly building on Epic's platform is another exhibit in Epic's antitrust defense that the ecosystem is open, so the franchise framing is doing double duty — distributing operational risk downward and the appearance of openness outward. Practical move for this week: find out who in your shop has authority to activate a connector, and whether that person knows they're also signing for it.

80/20Ask who signs off on connector activation. If the answer is an analyst in a queue rather than a named owner in governance, you have already accepted a liability transfer you never negotiated.

1,640 companies. 57 countries. One of them was a children's hospital.

Tech Times, with Drex DeFord (UnHack) · Aug 7–27, 2026

They didn't target us specifically — they targeted the people who have logins to us. A researcher named Vangelis Stykas spent 22 months inside a North Korean hacking group's own infrastructure and mapped 1,640 compromised companies across 57 countries, 700 to 800 of them badly. The entry point was a fake recruiter sending a developer a coding test that was malware — the tactic has a name now, contagious interview. Boston Children's was on the victim list. Nobody kicked in a door with a zero-day; they walked in as contractors who were supposed to be there. Some freelancers had active access to as many as 30 companies at once. So the real question isn't your perimeter, it's your third-party access list: the offshore dev team, the imaging vendor's engineers, the consultant who built your integration and still has a login eight months after go-live. Every health system has a vendor-risk questionnaire; almost none has a working answer to who still has a login. If you can't produce that list today, that's the finding.

Is your interoperability problem actually a chart-chasing problem?

HIT Consultant · Aug 27, 2026

Metriport raised $26M led by TJ Parker at Matrix, with ARTIS and Y Combinator, on a bet most interop pitches skip: the bottleneck isn't the exchange rails, it's that the record arrives as an undifferentiated pile a clinician can't use in the eight minutes they have. Read the product description carefully, because it's a claim about where the value sits — Metriport unifies and deduplicates records pulled from hospitals, pharmacies and outpatient clinics into a standardized, searchable model. The emphasis is on deduplication and search, not retrieval, and that's the tell. TEFCA and Carequality largely solved "can I get the documents." Nobody solved "can I answer a question at the point of care without reading 400 pages of duplicated CCDs." Their named customers have the most acute version of that problem: Amazon One Medical, Sollis Health, Color Health. At Sollis, physicians pull outside operative reports and imaging histories in real time. Total raised is $28.4M, so this is still an early bet — but a coherent one about which layer of the interop stack is actually scarce.

BuilderIf you're building on TEFCA rails, the retrieval is table stakes and the differentiation is entirely in what you do to the pile afterward. Deduplication, provenance and query are the product. Anyone still selling connectivity is selling the part that's about to be free.

Medicare Advantage satisfaction fell 41 points in two years — and CMS just retired the measures that were tracking why.

Wendell Potter · Aug 26, 2026

The national average dropped again on JD Power's latest survey — 12 points this year, 41 points since 2024, down to 611 on a 1,000-point scale across 14,559 enrollees in 12 markets. The sub-scores are the part that should worry you: trust down 49, satisfaction that coverage meets needs down 47, and only 43 percent strongly agreeing their insurer is a trusted partner. The variance inside single carriers is enormous, too — UnitedHealthcare finished first in Florida, Georgia and North Carolina and dead last in Michigan at 571. Humana's New York plan scored 554, the lowest plan in any market. So a single MA book isn't one thing; it's a dozen local businesses with wildly different member experiences. And the reason it won't show up cleanly in the dashboards going forward: CMS's 2026 Star Ratings overhaul eliminated 11 measures, several of which tracked complaints, appeals and call-center performance. We removed the instruments that would have flagged this.

HatersThere is a tidy version of this where Star Ratings go up next year and everyone declares progress. Stop measuring complaints and complaints stop appearing in the data. That is not the same as members being happier, and eight senators wrote to CMS in April to say so.

What do you say when your CFO reads that only 6% of companies got real money out of AI?

The Register · Aug 25, 2026

McKinsey surveyed 1,719 professionals. Thirty-seven percent attribute some EBIT impact to AI — flat versus last year — and only 6 percent attribute at least 5 percent of EBIT. Meanwhile 80 percent report individual productivity gains. The gap between those two numbers is the whole conversation, and healthcare converts between them worse than almost any industry. A clinician saving twenty minutes a day doesn't become margin unless something downstream absorbs it — another visit, a shorter length of stay, a role you didn't backfill. If nothing absorbs it, the productivity is real and the EBIT impact is zero, and you paid for both. Two more numbers worth carrying: 40 percent of billion-dollar-plus organizations are scaling agents, up from 27 percent, so the spend is accelerating regardless of the returns; and 20 percent say AI operating costs are now constraining their AI use, the first time cost has shown up as a brake rather than a line item. Nearly a third are building in-house with agentic coding tools instead of buying. The line to close on: name the absorption mechanism before you fund the pilot. "Saves clinicians time" is not a business case; "saves clinicians time, and here's the specific thing we'll do with that time" is.

Read the full wire ↗
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