---
title: "Shipping AI to a Million Patients Without an A/B Test"
category: "talks"
date: "2026-07-01"
time: "11:40am-12:00pm"
track: "AI in Healthcare"
room: "Track 7"
speakers: ["Jared Joselowitz"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "AI in Healthcare"
scheduleRoom: "Track 7"
scheduleLabels: ["AI in Healthcare", "Track 7", "session", "confirmed"]
---
# Shipping AI to a Million Patients Without an A/B Test

## Conference Context
- Date/time: 2026-07-01 · 11:40am-12:00pm
- Track/room: AI in Healthcare · Track 7
- Speaker(s): Jared Joselowitz
- Session type/status: session · confirmed

- Track: AI in Healthcare
- Room: Track 7
- Session type: session
- Status: confirmed

## Session Description
You can't A/B test on patients. You can't unsend a phone call. The model card won't save you at the post-incident review. Most AI eng playbooks assume the opposite. Ship to 5%, watch the dashboard, roll back if it goes wrong. None of it survives regulated deployment, which is now coming for fintech, legal, and government too. So the engineering has to move: into hazard analysis, simulated populations, asymmetric evaluation, and audit trails treated as the deliverable. The trail is the product. I'll show you what changes when rollback isn't an option. How Ufonia ships Dora, an AI voice agent now making clinical follow-up calls on the NHS and across US health systems, using a hazard-driven simulation rig (MATRIX) and a prompt-optimisation flywheel that surface failures and conform the same base system to each clinical niche, all of it pinned to an audit trail. And the cheap version of all this, for any team whose users can't be the test population.

## Media Evidence
No related AI Engineer channel video found yet.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
No linked video, transcript, or slide source has been attached yet.

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

## People
- [[jared-joselowitz]]

## Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.

## Synthesis
### Synthesized Breakdown
# Shipping AI to a Million Patients Without an A/B Test ## Conference Context - Date/time: 2026-07-01 · 11:40am-12:00pm - Track/room: AI in Healthcare · Track 7 - Speaker(s): Jared Joselowitz - Session type/status: session · confirmed - Track: AI in Healthcare - Room: Track 7 - Session type: session - Status: confirmed ## Session Description You can't A/B test on patients. You can't unsend a phone call. The model card won't save you at the post-incident review. Most AI eng playbooks assume the opposite.

### Speaker And Company Context
- [[jared-joselowitz|Jared Joselowitz]] — AI Research Engineer at [[ufonia|Ufonia]].

### Topics Covered
- [[agentic-search]]

### Derived Links And Source Material

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.