Short answer Do federal Medicaid rules address automated denials? Federal Medicaid managed care rules require that a denial be made by an individual with appropriate expertise. They do not mention automation at all. The rule exists and binds the decision to a person, and the silence is about the software that may have helped reach …
In a previous article we discussed constraining output space for small language model (SLM) narrow automation optimization. We mentioned at the time that this was the first in a short series of SLM optimization strategy articles. We are now at the second of those. This time we will focus on the reuse of the prompt …
Reusing the Prompt Prefix with a Key-Value Cache for SLM Optimization Read More »
Short answer Do Medicaid managed care rules cover automated denials? Medicaid managed care already has a rule: a denial must be made by an individual with appropriate expertise. It does not mention automation. Regular Medicaid has no equivalent rule on who decides. Federal advisers asked for guidance on one and a rule change on the …
Medicaid Managed Care and Automated Denial · Hanh D. Brown Read More »
There is a moment happening in offices and bedrooms all over the world right now, and it looks like this. Three AI agent sessions are running. One is refactoring something. One is writing tests. One is halfway through a migration nobody wanted to do by hand. The person in front of them is not typing. …
AI Made Me 5x Faster. It Also Made Me 5x Worse at My Job. Read More »
Short answer How do algorithms decide how many home care hours you get? Algorithms decide home care hours by turning an assessment into a score, and the score sets the number. States run this through Medicaid waivers, and some now use such a tool. A cut needs written notice naming the reason and the rule. …
Algorithms Decide How Many Home Care Hours You Get · Hanh D. Brown Read More »
Prompt optimization and prompt engineering get used interchangeably online, and that’s causing more confusion than it should. Prompt engineering designs a prompt from scratch; prompt optimization refines a prompt you already have, through specificity, structure, and iteration, without touching the model itself. That distinction matters because most people asking “how do I get better output …
5 Prompt Optimization Strategies That Actually Improve LLM Output Read More »
Short answer Can prior authorization and utilization review be done by machine? Prior authorization and utilization review can be automated in part, but the refusal itself needs a person. Texas bars a utilization review agent from using an automated decision system to make an adverse determination, wholly or partly. Federal rules name a human but …
Prior Authorization and Utilization Review by Machine · Hanh D. Brown Read More »
Table of contents ITSA and why it matters A brief introduction ITSA assumptions and when to use it (and when you shouldn’t) Why a multi-agent system to run ITSA? ITSAgentic: an AI product to run Interrupted Time Series Analysis The importance of exposure share Encoding diagnostic checks for the main assumptions Are the results and …
How I Built a Multi-Agent System for Interrupted Time Series Analysis (ITSA) Read More »
Short answer Is AI deciding Medicare coverage? AI is not deciding Medicare coverage on its own. Medicare runs a pilot using artificial intelligence to review some prior authorization requests in six states, covering Original Medicare only. Under Medicare Advantage a licensed clinician must review any denial based on medical necessity. Medicare began an experiment this …
AI Is Deciding Medicare Coverage · Hanh D. Brown Read More »
Today, we’re introducing two new models that bring advancements in near real-time reasoning to more effectively enable voice agents and make conversing with AI feel more intuitive and intelligent. Gemini 3.8 Live: Built for scale and cost efficiency, combining conversational intelligence with fluid dialogue and visual grounding. Gemini 3.8 Live Extended Thinking: Built for high-complexity …
Gemini 3.8 Live & Gemini 3.8 Live Extended Thinking Read More »
