Markdown source

Evals Driven-Development: Engineering a Mental Health AI Coach Ethically & Safely

Conference Context

Session Description

In the world of AI Mental Health, vibes can be dangerous with real consequences. Building Sondermind’s Mental Health AI Coach required us to invent a new playbook for Eval-Driven Development in order to balance effectiveness and safety. This session is for the builders who want to see how to handle the most difficult edge cases in the agentic world. We’ll show how we’ve built a Clinical Feedback Loop that turns human therapist insights into machine-readable evaluations in a production system with thousands of conversations. We’ll dive into: - The Ethics Engine: Building and calibrating modular guardrails that can be updated as clinical guidelines evolve. - Agentic Oversight: Why we moved from single-prompt agents to a closed-loop Supervisor/Executor/Evaluator pattern to ensure clinical adherence. - Human Oversight: How we monitor Sonder to ensure that we can improve safety and quality with clinical feedback.

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

Notes

Synthesis

Synthesized Breakdown

Evals Driven-Development: Engineering a Mental Health AI Coach Ethically & Safely ## Conference Context - Date/time: 2026-06-30 · 2:50pm-3:10pm - Track/room: Evals · Track 5 - Speaker(s): Akele Reed, Dave Revere, Doug Keller - Session type/status: sponsor · confirmed - Track: Evals - Room: Track 5 - Session type: sponsor - Status: confirmed ## Session Description In the world of AI Mental Health, vibes can be dangerous with real consequences. Building Sondermind’s Mental Health AI Coach required us to invent a new playbook for Eval-Driven Development in order to balance effectiveness and safety. This session is for the builders who want to see how to handle the most difficult edge cases in the agentic world. We’ll show how we’ve built a Clinical Feedback Loop that turns human therapist insights into machine-readable evaluations in a production system with thousands of conversations.

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

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.