Listen to this episode on: Spotify | Apple Podcasts
How do you build an AI product for an audience that can’t afford to be wrong—and won’t trust you until you prove it?
In this episode of Just Now Possible, Teresa Torres talks with three leaders from Healio—Jennifer Deal (SVP of Product Development), Casey Utley (Senior UX Designer), and Matthew Skepner (VP of Technology)—about how their 125-year-old medical publishing company built Healio AI, an AI-powered assistant that helps physicians prepare for patient care.
They share how a survey of 300 healthcare professionals shaped their early assumptions, why physicians surprised them by asking for help with patient communication rather than diagnostics, and how they built a working prototype in a single weekend using Cursor. You’ll hear how they combined RAG with hybrid search across trusted sources like PubMed, designed citation UX that physicians actually trust, and set up eight LLM judges alongside real physician feedback to evaluate response quality.
If you’re building AI for a high-stakes domain where trust, accuracy, and transparency matter more than speed, this conversation is packed with practical lessons.
Show Notes
Guests
- Jennifer Deal – SVP of Product Development, Healio
- Casey Utley – Senior UX Designer, Healio
- Matthew Skepner – VP of Technology, Healio
What we cover in this episode:
- Why physicians need AI at the point of care—and how they actually use it (hint: it’s preparation, not bedside)
- The surprising discovery that physicians wanted help with patient communication and empathy, not just clinical answers
- Building a working prototype in a weekend with Cursor after starting with Figma mockups
- How Healio’s RAG system combines lexical search, vector search, and semantic search across multiple trusted sources
- Why “just use PubMed” isn’t simple—five different ways to access the same data, each with trade-offs
- Designing citations that physicians trust: subscripts, hover states, and progressive disclosure
- Serving contextual ads while the LLM processes queries—a practical monetization approach
- HIPAA compliance and input guardrails for masking personal health information
- Eight LLM judges for evals: safety, medical accuracy, faithfulness, relevancy, completeness, reasoning, clarity, and overall quality
- Why physician feedback trumps LLM-as-judge feedback in high-stakes medical contexts
- The role of the Healio Innovation Partners in ongoing discovery and validation
Resources & Links
- Healio — Medical news, education, and clinical guidance for healthcare professionals
- PubMed — Database of biomedical literature
- Cursor — AI-powered code editor used to build the prototype
Chapters
00:00 Introduction to Jen, Casey, and Matt
01:30 What Healio Does: Medical News and Education
03:15 The Problem Space: Information Overload at Point of Care
05:45 Surveying 300 Healthcare Professionals
08:20 The Surprising Discovery: Patient Communication Over Diagnostics
11:00 How Physicians Actually Use Healio AI
13:30 Building a Working Prototype in a Weekend
16:45 The Architecture: Hybrid Search and RAG
20:10 Why Accessing PubMed Isn’t Simple
23:00 Designing Trust: Citations and Source Transparency
26:30 Contextual Advertising During Query Processing
28:45 HIPAA Compliance and Input Guardrails
31:20 Eight LLM Judges: Building an Eval System
35:00 Why Physician Feedback Trumps LLM Feedback
38:15 Ongoing Discovery with Healio Innovation Partners
41:00 What’s Next for Healio AI
Full Transcript
Podcast transcripts are only available to paid subscribers.
