<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>AI on transtorm.ai</title>
		<link>https://transtorm.ai/tags/ai/</link>
		<description>Recent content in AI on transtorm.ai</description>
		<generator>Hugo</generator>
		<language>en</language>
		
		
		
		
			<lastBuildDate>Wed, 21 Oct 2026 00:00:00 +0000</lastBuildDate>
		
			<atom:link href="https://transtorm.ai/tags/ai/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>Securing a medical voicebot without slowing it down</title>
				<link>https://transtorm.ai/blog/secure-medical-voicebot-without-slowing-it-down/</link>
				<pubDate>Wed, 21 Oct 2026 00:00:00 +0000</pubDate>
				<guid>https://transtorm.ai/blog/secure-medical-voicebot-without-slowing-it-down/</guid>
				<description>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.</description>
			</item>
			<item>
				<title>Qwen3.8-Flash-Next applies the fundus laterality rule backwards</title>
				<link>https://transtorm.ai/blog/qwen-fundus-laterality-reversed-rule/</link>
				<pubDate>Sat, 26 Sep 2026 00:00:00 +0000</pubDate>
				<guid>https://transtorm.ai/blog/qwen-fundus-laterality-reversed-rule/</guid>
				<description>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.</description>
			</item>
			<item>
				<title>Decision models (1): you don&#39;t need a thousand words to decide</title>
				<link>https://transtorm.ai/blog/decision-models-1-you-dont-need-a-thousand-words-to-decide/</link>
				<pubDate>Fri, 18 Sep 2026 00:00:00 +0000</pubDate>
				<guid>https://transtorm.ai/blog/decision-models-1-you-dont-need-a-thousand-words-to-decide/</guid>
				<description>For three years, we have been asking models built to write to make decisions. A new family of models does nothing but decide. First part: what a decision model is, with Jev and SemIf.</description>
			</item>
			<item>
				<title>Decision models (2): what speed changes</title>
				<link>https://transtorm.ai/blog/decision-models-2-what-speed-changes/</link>
				<pubDate>Fri, 18 Sep 2026 00:00:00 +0000</pubDate>
				<guid>https://transtorm.ai/blog/decision-models-2-what-speed-changes/</guid>
				<description>A decision model that answers in a hundred milliseconds is not used the way a language model that answers in ten seconds is. Decision loops, comparing hypotheses, the generator-and-judge pairing, and the return of the small specialized model: the second part of our article on Jev and SemIf.</description>
			</item>
			<item>
				<title>Job50&#43;</title>
				<link>https://transtorm.ai/usecases/job50/</link>
				<pubDate>Wed, 19 Aug 2026 00:00:00 +0000</pubDate>
				<guid>https://transtorm.ai/usecases/job50/</guid>
				<description>&lt;h2 id=&#34;test-a-market-hypothesis-at-scale-without-burdening-your-research&#34;&gt;Test a market hypothesis at scale, without burdening your research&lt;/h2&gt;&#xA;&lt;p&gt;Job50+ is an online job platform project dedicated to candidates over 50.&lt;br&gt;&#xA;In a Lean Startup approach, the goal is to better understand how different recruiter profiles perceive this value proposition, what barriers they encounter, what could convince them to use such a platform, and in what contexts the interest is strongest.&lt;/p&gt;&#xA;&lt;p&gt;To answer this, it wasn&amp;rsquo;t enough to conduct a few isolated interviews. We needed to explore a large number of recruiter profiles, compare the results between segments, and naturally surface actionable insights in a structured way.&lt;/p&gt;</description>
			</item>
			<item>
				<title>Recruitment Tool</title>
				<link>https://transtorm.ai/usecases/recruitment-tool/</link>
				<pubDate>Wed, 19 Aug 2026 00:00:00 +0000</pubDate>
				<guid>https://transtorm.ai/usecases/recruitment-tool/</guid>
				<description>&lt;h2 id=&#34;context&#34;&gt;Context&lt;/h2&gt;&#xA;&lt;p&gt;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.&lt;/p&gt;</description>
			</item>
			<item>
				<title>A &#34;simple&#34; web form: the hidden work behind a surgical eligibility simulator</title>
				<link>https://transtorm.ai/blog/eligibility-simulator-hidden-work/</link>
				<pubDate>Mon, 20 Jul 2026 00:00:00 +0200</pubDate>
				<guid>https://transtorm.ai/blog/eligibility-simulator-hidden-work/</guid>
				<description>A clinic specialised in refractive surgery wanted an honest eligibility simulator. Behind five questions sit a surgeon&amp;rsquo;s real rules, a logic of caution, and total privacy.</description>
			</item>
			<item>
				<title>Hiring Without Trusting Your Gut: The Tool We Built for Our Interviews</title>
				<link>https://transtorm.ai/blog/interview-recruitment-tool-weighted-ranking/</link>
				<pubDate>Mon, 15 Jun 2026 00:00:00 +0200</pubDate>
				<guid>https://transtorm.ai/blog/interview-recruitment-tool-weighted-ranking/</guid>
				<description>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.</description>
			</item>
			<item>
				<title>Business Process Automation: Our Method for Deploying Reliable Micro-Processes</title>
				<link>https://transtorm.ai/blog/business-process-automation-method-micro-processes/</link>
				<pubDate>Sun, 08 Mar 2026 00:00:00 +0000</pubDate>
				<guid>https://transtorm.ai/blog/business-process-automation-method-micro-processes/</guid>
				<description>Discover the transtorm.ai method for reliable business process automation: an audit of the real process, human validation on important decisions, complete anonymization of data sent to external resources, robust integrations, and continuous improvement.</description>
			</item>
	</channel>
</rss>
