Skip to content

Following are my personal thoughts on tech, AI, startups and adoption of AI in Health-Care. You could read more about me here

Subscribe on Substack

Blog / Thoughts

  • 11 min read

CMS ACCESS: An Engineer's Field Guide

The reimbursement for ACCESS is small and I'm not going to relitigate it here. What I'll say is that this is the first CMS model I've worked on where a technology-enabled care organization is the aligned participant, gets an eligibility answer from the payer directly, reports the instrument answers and scored values rather than a summary measure, and can ask for the claims afterward. Whether that combination pays for itself depends on acquisition and retention, which was the previous post, and on how much of the intake, record, and reporting work carries over to the next program, which I don't know yet. My bet is most of it. This post is the technical half of that bet.

Back in March I built a mock ACCESS FHIR server against a draft of the spec, mostly to find out what a year of this model would look like end to end. Since then we've sent real packets to CMS's test environment and aligned real patients in the MSK track at RevelAI. So this is what the API actually asks of you, what the packets look like, what CMS's test environment taught us, and the system you end up building around it.

If you're not the one writing the client, here's the short version:

  • The API is four operations and one poll. Getting a client to talk to CMS is the easy part, and it's mostly done once it can submit and read a result code.
  • The hard part is a year of engagement per patient, with a record good enough to bill from and outcomes reported on CMS's clock.
  • The thing worth more than the payment is the loop: eligibility from the payer itself, outcomes on a schedule, and claims data you can ask for. I'll come back to that.
  • 6 min read

I Built My Agent Computer in the Cloud

I live in Ashburn, Virginia. Home of the data center. There's a stat that goes around that two thirds of US internet traffic passes through Ashburn. So it felt right that my agents should live here too. I rented a machine through OVH, a good Linux box that stays on, in a data center in Virginia. 16 cores, 62 GB of RAM, two NVMe drives in RAID1. I pay about $90 a month for it.

  • 9 min read

CMS ACCESS: Getting the Patient in the Door Is the Hard Part

It's very hard to automate patient referrals into a digital health program. You'd think patients will see a program like CMS ACCESS online and onboard themselves, but there's a lot more to it.

We've spent past months at RevelAI Health building for this model, and most of that time went into a problem that isn't in the RFA at all: how does a patient actually get into your program, and how do you keep them there for twelve months? I want to share how we think about it, what the evidence says, and what we're building.

  • 5 min read

The Agent That Cheated on Its Own Exam

Picture a student in a proctored exam. Sealed room, no phone, one door, someone watching. Now picture that student quietly working out that the answer key is sitting in a filing cabinet three buildings over, letting itself out through the ceiling, and going to get it.

That is more or less what happened to Hugging Face in July. Except the student was an AI agent, and the filing cabinet was production.

A month later, OpenAI published what preventing the next one costs. The number is denominated in GPUs.

  • 6 min read

The Learning Loop: A Data Agent That Audits Its Own Answers

Text-to-SQL is a demo. Keeping the numbers right for months while the schema moves underneath you is the actual product. Byaan closes that gap with auto-evolving skills: every conversation gets adversarially reviewed, mistakes become skill edits backed by code evidence, ambiguity becomes a question, and subject matter experts hold the merge button.

  • 6 min read

The LLM Router Era Starts with Fable 5

Fable 5 is the most incredible model I have used. Not a nicer version of the last one. Another level of increment in capability.

But that is not the part that stuck with me. After days of heavy use, the thing I keep noticing is not what Fable does. It is what Fable chooses not to do itself.

It delegates. And it is good at it. That is the first real glimpse of something I have been waiting for: the LLM router era. This post is the thesis and the playbook: why routing is about to become the default economics, and the exact skill I use to make Fable route work to cheaper models.

  • 5 min read

A Few Weekends with a Coding Agent Replaced My $30/Month Email App

I used to be slow at email. Threads sat unread for days. Replies took a weekend of guilt. Archiving was something I did with a mouse, one click at a time.

Superhuman fixed that. It taught me that email is a keyboard problem. c to compose, e to archive, j and k to move, Cmd+K for everything else. Within a month I stopped treating my inbox as a place I visit and started treating it as a queue I clear.

So this is partly a thank-you note. Superhuman genuinely made me productive at email, and I paid $30 a month for years, happily.

  • 6 min read

Plan Big, Execute Small: Taming My Fable 5 Bill Without Dumbing It Down

I run Claude Fable 5 as my daily driver in Claude Code. It is the best model I have used, and it is priced like it: $10 per million input tokens, $50 per million output. The painful part is that most of what an agent does all day is not deep reasoning. It is reading. Files, web pages, logs, search results, all pulled through the most expensive brain money can buy.

Then I found an Anthropic cookbook that reframed the whole problem: Plan Big, Execute Small. One notebook, one idea: let the frontier model plan and judge, let cheaper models do the mechanical reading. I liked it enough that I turned it into a Claude Code skill, and it has changed how I work.