Self-hosted on transtorm.ai

Securing a medical voicebot without slowing it down

Wed, 21 Oct 2026 00:00:00 +0000

How we secured Camille, the voice assistant for several medical centers: lightweight local infrastructure, decision models alongside the LLM, and prompts and connections optimized to answer in about one second.

Qwen3.8-Flash-Next applies the fundus laterality rule backwards

Sat, 26 Sep 2026 00:00:00 +0000

Qwen3.8-Flash-Next locates the optic disc correctly in 120 decisions out of 120, then gets the eye wrong on 51 images out of 60. The protocol, the numbers and the fix we adopted.

A Custom-Built Application for an Accurate Patient Journey Audit

Sat, 22 Aug 2026 00:00:00 +0000

Our patient journey audits rested on durations reconstructed from memory. We built an application that follows our existing outline, times the visit as it happens and walks through its checklist before exporting the report.

Recruitment Tool

Wed, 19 Aug 2026 00:00:00 +0000

Context

Recruiting means comparing people met several days apart, based on notes scribbled on the fly and impressions that fade fast. By the end of a round of interviews, the notes are scattered between a notebook and a file, the memory of the first candidate is already blurry, and the decision naturally leans toward the last person met or the most likeable one. Intuition keeps its place, but it should not be the only judge.

Hiring Without Trusting Your Gut: The Tool We Built for Our Interviews

Mon, 15 Jun 2026 00:00:00 +0200

To hire our junior developer, we built a small web application that brings together the context of the role, the candidate profile, interview note-taking, scoring, and a weighted ranking. Data stays local, code is open on GitHub.

How a Reception Kiosk Builds the Clinical Worklist Itself

Sat, 06 Jun 2026 00:00:00 +0000

How a patient check-in kiosk for an ophthalmology practice goes beyond mere registration: it identifies the patient, infers the consultation type from the last follow-up, and automatically creates the worklist item in the patient record, with a mobile companion, secured by physical presence, on which patients can see how late their doctor is likely to be running, self-hosted and GDPR-friendly. A comparison with Phreesia, Clearwave, Qmatic and the patient kiosk market.