Framework
Build for Signal, Not Assumption
When training models for human behavior, go in with as few assumptions as possible. Let the data surface the features. Your intuitions about what matters are often wrong.
How it works
- 1The temptation is to say 'squinting eyes mean X' or 'flat voice tone means Y' before you have the data to back it up. Starting from assumptions bakes bias in from the beginning.
- 2Videra's approach: collect voice, video, and language features broadly, run structured clinical screeners alongside them, and let the model find which features actually predict the outcome.
- 3Then apply the sniff test: does it make sense that this feature is predictive? And does it hold across demographic groups?
- 4The bias version of this failure is Amazon's hiring model — trained only on high-performing men, it learned to predict that men perform better. The data was wrong because the training set was wrong.
- 5One critical behavioral predictor Videra found: whether a substance use patient sleeps at night predicts treatment completion and sobriety at 12 months better than almost any other signal. Nobody assumed that. The data surfaced it.
Hear it on the podcast
The Behavioral Health Crisis Is a Data ProblemListen to the episodeMore from this episode
The Continuity GapThe most valuable data in healthcare — and in most SaaS products — exists between appointments, not during them. Building for the gap is the actual product opportunity.The Paying Problem FilterCool technology that no one will pay for is not a product. Before you fall in love with your insight, find the customer whose budget line it solves.The Bias Audit TriadThree practices that prevent AI models from encoding discrimination: clean and representative data, demographic testing before launch, and continuous monitoring for drift.
Get the next framework first
One email a week with the frameworks, tools, and founder stories from the podcast. Free.
More frameworks for AI & Automation
The Centralized Data LayerOne AI data analyst serving the whole company beats fifteen teams building their own agents from different sources.Build for Agents, Not Just HumansAgents have fundamentally different interface preferences than humans. Designing for both requires treating them as separate audiences.The Three Stages of Data IntelligenceMost companies are stuck at Stage 1. The real value - and the real competitive advantage - lives in Stages 2 and 3.Agent Access Control as a Safety FoundationYou cannot let agents go wild if they have read-only access to two tables. Granular permissions are the foundation of safe agentic deployment.Context Over ModelThe AI model you use matters far less than the quality and completeness of the context you feed it. Managing context is the real competitive advantage.Personal AI LibrarianAn AI that knows everything in your library — and only your library. Trust through constraint.