Building AI for healthcare leaves zero room for error.

I’m currently collaborating with an incredible team on Raphald AI, a medical detection application. Building the systems for a project with stakes this high is a massive reminder that the underlying backend architecture matters just as much as the machine learning model itself.

When integrating diagnostic AI, your API endpoints cannot drop requests, and your database workflows demand absolute integrity. You aren't just passing JSON payloads; you are handling critical, real-time workflows where stability is non-negotiable.

Engineering these systems continues to shape my approach to building robust Python backends. If you are developing a product that requires reliable AI integration or rock-solid FastAPI infrastructure, check out the newly updated services on my profile. Let's build something that works when it counts.

Behind the scenes on how our build process actually changed this month.

For most of this year we ran AI under a budget constraint, and that constraint quietly shaped everything. Which problems we pointed AI at. Which we did by hand. How much of a codebase we were willing to let a model read. Scarcity was the organising principle and we had stopped noticing it was there.

Then it lifted. Here is what actually broke.

The problem nobody warned us about. Freed from budget pressure, sessions got long and deep. A model will happily work a huge problem in one sitting. But the sitting ends — timeout, full context, or you go to bed. And everything it worked out along the way vanishes. The dead ends it ruled out. The constraint it discovered in hour two. The reason it chose one approach over another.

When sessions were short, we held that context in our heads. When they got long, we couldn't. We started losing more to forgotten context than we had ever lost to rate limits.

What we built to fix it:

Exit interviews. Before closing any meaningful session, we prompt the model for a handover briefing — what it did, what it decided, what the next instance needs. Not a commit message. An actual briefing. That output becomes the opening context next time. This is the single highest-leverage thing we changed and it took an afternoon to adopt.

Browser session stability. Long builds kept dying when whoever was driving switched tabs. Moving active sessions into the Chrome extension fixed it. Unglamorous. Recovered more hours per week than any clever prompting.

Logic only, no UI. We kept fighting the same battle — strong architecture and logic coming back attached to cluttered, incoherent interfaces. So we stopped asking. We now prompt for logic and architecture and explicitly block frontend generation. Structural foundations go to a human who builds the interface natively. Restricting the model made the output better, which is not what I expected.

Two-stage handoff. Fast rough first pass to kill ambiguity, often straight from a client scope document — one was 125 pages fed through in a single stretch. Then a different person takes the careful second pass.

The part I did not expect. More capacity meant more verification, not less. We increased the QA burden at the same time we removed the ceiling, deliberately, because an agentic system will always find something to report and the report will always sound like progress.

The tools were the easy part. The reorganisation was the work.

Full write-up: https://infiniteup.dev/the-bottleneck-moved-how-we-rebuilt-our-workflow-around-mcp-and-fable/

budget shaping the whole process, good honest writeup