Healthcare’s Agent Bytecode: X12 as the Harness for AI Agents — Vasant Kearney, Onlay
Call the payer, open their web portal, and read their X12 feed, and all three can tell you the patient is covered. You treat the patient anyway, and the claim comes back denied because they were not covered at the time. Vasant Kearney's point is that none of those surfaces is ground truth. A payer's phone system, portal and X12 layer are often built by different teams, sometimes by different contractors entirely, so they can contradict each other and they can just as easily agree on the wrong answer together.His response is to treat X12 as a harness rather than a file format. Models do their best work confined, the way a strict language confines, and X12 already encodes the contract between a provider and a payer. Every stage of the claim lifecycle has an X12 correspondence, from an eligibility check as a 270 through the 999 that acknowledges syntax to the 835 that records payment, so an agent placing a phone call or driving a portal is emitting the same transaction by another route. Everything normalizes into an internal representation held as correct only until downstream evidence says otherwise. Two constraints travel with it. Memory has to live in a database rather than on local disk the way coding agents do it, for logical separation. And a stronger model cannot simply be dropped in, because better on a benchmark is not the same as better inside a system built around the model it replaces. He describes the posture as being AI pilled and AI skeptical at once.
Speaker info:
- https://x.com/vasantkearney
- https://www.linkedin.com/in/vasant-kearney-7b7a48b3
- https://onlay.ai/
Timestamps:
0:00 - Reading the room
1:06 - The goal is cost and patient experience
1:58 - How we arrived at an execution layer
3:06 - Solving handwritten digits does not cash the check
4:42 - What gets lost when you flatten a multimodal record
6:16 - What the agentic execution layer actually touches
7:23 - Why enterprise memory cannot live on local disk
7:49 - A better model is not automatically better for you
8:31 - Harness, and why X12 belongs in it
9:44 - Fifty steps, error propagation, and the cost of pure reasoning
11:16 - Memory that helps without steering the user
12:36 - The claim lifecycle, transaction by transaction
13:29 - A phone call is an X12 transaction underneath
14:47 - The schema is public, so agents can look it up
15:30 - X12 is a system of rules, not ground truth
16:47 - Normalizing to an internal representation
19:02 - Be AI pilled and AI skeptical Receive SMS online on sms24.me
TubeReader video aggregator is a website that collects and organizes online videos from the YouTube source. Video aggregation is done for different purposes, and TubeReader take different approaches to achieve their purpose.
Our try to collect videos of high quality or interest for visitors to view; the collection may be made by editors or may be based on community votes.
Another method is to base the collection on those videos most viewed, either at the aggregator site or at various popular video hosting sites.
TubeReader site exists to allow users to collect their own sets of videos, for personal use as well as for browsing and viewing by others; TubeReader can develop online communities around video sharing.
Our site allow users to create a personalized video playlist, for personal use as well as for browsing and viewing by others.
@YouTubeReaderBot allows you to subscribe to Youtube channels.
By using @YouTubeReaderBot Bot you agree with YouTube Terms of Service.
Use the @YouTubeReaderBot telegram bot to be the first to be notified when new videos are released on your favorite channels.
Look for new videos or channels and share them with your friends.
You can start using our bot from this video, subscribe now to Healthcare’s Agent Bytecode: X12 as the Harness for AI Agents — Vasant Kearney, Onlay
What is YouTube?
YouTube is a free video sharing website that makes it easy to watch online videos. You can even create and upload your own videos to share with others. Originally created in 2005, YouTube is now one of the most popular sites on the Web, with visitors watching around 6 billion hours of video every month.
