In this session, we explored why agentic AI can be risky: models can sound confident while hallucinating, skipping required steps, or overstepping their authority. We covered semantic authorization, granting permissions based on meaning, context, and output quality, and demoed a control-plane pattern that enforces pre-checks, calibrates thresholds against known-good responses, and records a full audit trail tied to a human owner for real workflows.

During the discussion with Span, we talked about a challenge many eng leaders are navigating: AI is increasing coding throughput, but overall delivery impact can feel flat as code review, rework, and quality bottlenecks emerge. We also discussed what it would take to measure AI impact day-to-day: going beyond vanity metrics and surveys to instrument the full SDLC, surface actionable insights, and tie adoption to quality and cost.

During the discussion with Ren, we chatted about a challenge many engineering leaders are feeling: real people development keeps getting squeezed by meetings and delivery pressure, even as expectations for feedback and growth rise. We also discussed what it would take for AI-assisted coaching to work day-to-day: low-friction usage, integration with existing workflow artifacts, clear privacy boundaries, and nudges that improve the quality of human conversations.