Building @AbridgeHQ + random musings at intersection of Warp records, late 90s skateboarding, Vincent Van Duysen, and cardiology.
Joined November 2012
- Tweets2.1K
- Following2.7K
- Followers3.9K
- Likes6K
Pinned Tweet
Our thesis at @AbridgeHQ has always been simple: the best technology in healthcare should help the technology disappear.
This is our opportunity to use AI to actually rethink and redesign the system.
Learn more here: abridge.com/vision?utm_sourc…
Shiv Rao, MD retweeted
Abridge CEO @ShivdevRao believes healthcare still hasn’t grasped what an AI-native company looks like.
With ambient clinical documentation as the wedge, @AbridgeHQ is now expanding to build for the processes that occur before and after the visit.
Their goal is to craft a healthcare tool that can handle everything from risk adjustment and care gap closure to note-taking. The idea is to provide whatever the clinician or patient needs, with AI assistance.
Shiv explains their mission to Lightspeed Partners Dr. @BrentonFargnoli and Dr. @GalymImanbayev.
When he thinks about approaching problems in healthcare, Shiv zooms in on the end user’s perspective. He asks what an enterprise-grade assistant for a doctor would look like, and how Abridge could build one:
“Some of these outcomes could be financial, but aspirationally, these outcomes should be clinical.”
Watch the full interview below.
00:00 The Clinic Prep Vision: Abridge Working Behind the Scenes
01:43 From History Major and Skateboarder to Physician
07:12 Cardiology and the First Healthcare Software Project
11:57 What Abridge Is Today: Building an AI-Native Health System
15:21 Clinical Jobs the Assistant Can Do: The PET Scan Example
20:09 Pre-Charting Reimagined: Gaps, Prior Auths, and Clinical Trials
24:15 Computer Use Demo: From Generative AI to Actions
28:17 The North Star: A Cardiologist Who Retired Too Early
30:02 Clinician Scientists: Building for Doctors, by Doctors
33:03 Open Weights and Staying Adaptable
39:56 Scaling AI Across the VA
43:27 Life Sciences and Public Health: Spotting an Outbreak Early
46:06 Rearchitecting the Provider and Payer Relationship
52:44 Rapid Fire: Overrated, Underrated, and Investor Advice
Health systems have put years of clinical expertise into defining how they can best care for their patients, and those guidelines should be accessible when a clinician is making a decision.
Today, @AbridgeHQ announced support for local pathways, a new capability within the Abridge Assistant that brings a health system’s preferred care plans into responses, alongside relevant medical literature and contextualized to the patient.
With local pathways, a clinician doesn’t have to go searching for the next step. We are bringing that institutional knowledge into the same Assistant, and into the same workflow, that clinicians use to understand the patient and consult the evidence.
Read more here: abridge.com/press-release/lo…
At @AbridgeHQ, it is a privilege to serve Veterans and the clinicians who care for them.
Shiv Rao, MD retweeted
Landed in Chicago for #ScientificSessions26. Tomorrow at 9:15 AM CT in the Health Innovation Pavilion: one clinical problem from the room, one AI agent, built in real time. Come help me pick the problem! @AHAScience @AbridgeHQ #AHA26
Shiv Rao, MD retweeted
My new piece in @NEJM_AI, "Vibe Coding versus Clinical Reality": the barrier to building has dropped, but the barrier to building safely hasn't. Physicians can now prototype; getting it safely to patients still takes engineers working alongside us.
ai.nejm.org/doi/full/10.1056…
The Brain Injury That Made a Middle-School Teacher a Musical Genius nytimes.com/interactive/2026…
+
Weight-Space Programming
xitter.twitterapi.xyz/rikiyatakehi/status/21…
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
2
11
796
Shiv Rao, MD retweeted
and just like that 🫰
xitter.twitterapi.xyz/morgancheatham/status/…
The @AbridgeHQ Assistant is the AI assistant for healthcare.
Our vision is that every clinician has a team of agents figuring out all the things they want to know, helping them ask the right questions, leverage the right evidence, and improve patient care and outcomes.
Now in use at 300+ health systems.
Shiv Rao, MD retweeted
“What’s changed since this patient’s last visit?”
Ask the Abridge Assistant. Explore the chart and clinical questions with available patient context and cited evidence.
The same chat supports medical calculators pre-filled with available patient data and draft documents, such as referral letters. Review the sources and calculator inputs; edit drafts before use.
See the Abridge Assistant in action: abridge.com/assistant
Our very own
Grateful to @NEJM_AI for having me on Grand Rounds. The barrier to building has dropped, but the barrier to building safely hasn't. Closing that gap is what we do every day at @AbridgeHQ.
Excited to back @kevinweil and Warp Sciences 🚀
Kevin has been an awesome friend / advisor / investor of ours over the years. Excited to see him and @dpatil build in healthcare / life sciences 🙌.
💥 Introducing Warp Sciences, a new company applying AI and robotics to help the world develop new medicines faster.
We’ve raised a $215M Series A led by @lightspeedvp to bring frontier AI out of the browser and into the lab, and build scientific capacity here in America.
I co-founded Warp with my long-time friend @dpatil, FAIR co-founder @manohar_paluri, and drug hunter Sol Reisberg. The early team is full of incredible people like @bkspears9, who helped achieve Q>1 fusion at LLNL.
Pre-charting. Context-aware decision support. Medical calculators with chart values already filled in. Draft handoffs and referral letters.
1
3
150
Abridge Assistant helps clinicians prepare, brings relevant information into the workflow, and gets the first draft done. Clinicians bring the judgment.
abridge.com/blog/abridge-ass…
1
4
142
Shiv Rao, MD retweeted
Thought I’d share a personal story from before we invested in @AbridgeHQ:
I was taking my son to his annual check-up at Sutter Health.
When we got there, the doctor asked us if we’d be open to trying new AI tech that documents visits.
I asked for the name of the company and she told me it was Abridge.
My investor curiosity started kicking in, so I told her I was excited to try it.
She launched the app and started recording the entire check-up. During the meeting, she asked my son the typical playful questions like “Do you have 120 toes?” or “Is that a Dinosaur in your ear?”
But when we checked the EHR, everything had been pulled in w/ no mention of dinosaurs or extra toes - crazy.
Investor curiosity kicked in again so I asked her if the product was “sticky.”
She basically told me they couldn't live w/o Abridge.
At that point in time, I had heard about the company but hadn’t realized how impactful it’d become w/ frontline users. So as soon as I got home I started digging.
We did our research at the fund, made the connections, and eventually backed the company.
Thrilled to see them changing people’s lives.
Shiv Rao, MD retweeted
That's a wrap for Abridge VP of Product Janie Lee on @MTSlive!
Key takeaways:
-- Abridge Assistant has been the fastest-growing product in Abridge history
-- Context-aware clinical intelligence—patient chart data is crucial for decision support
-- Clinician jobs are changing. The future of AI is supporting them
My first time caring for Veterans was at the VAMC in Ann Arbor. What began there became a weekly VA clinic for nearly eight years, first in Ann Arbor and later in Pittsburgh.
What always stayed with me was how much Veterans had given in service and how little they asked for in return.
At @AbridgeHQ, we’ve had the opportunity to improve the care delivery experience for many more Veterans than I could have ever seen as a doctor in a clinic. We’ve supported VA clinicians with cutting edge tools that help them spend less time staring at a computer screen and more time focusing on the Veteran in front of them.
We started with a pilot deployment at 5 VA medical centers, which has since grown to more than 75 sites across the country.
Now, Abridge has been selected to bring our clinician intelligence platform to Veteran care nationwide through the VA enterprise contract for ambient AI.
As the VA undertakes one of the largest electronic medical record transitions in history, its clinicians remain committed to delivering exceptional care to Veterans. They deserve tools that ease documentation demands, create more space for connection during each encounter, and help preserve important details across visits and care teams.
Abridge meets VA clinicians where they are, by being fully operational on both VistA/CPRS and the Federal EHR.
This is the level of care that Veterans deserve and the VA's mission demands.
It is our privilege to serve the needs of those who have served and the clinicians who care for them.
abridge.com/press-release/va…
