Videos

Building an eval platform for AI agents is fundamentally a systems problem, not a UI or spreadsheet issue, because...

Most teams ship AI features on vibes—testing a few queries manually and shipping—but this breaks as...

Transcripts alone are dangerously insufficient for debugging voice agents because they miss audio-specific failures...

Evals are reliability instrumentation for non-deterministic AI systems, analogous to fuzzy unit tests. The talk...

Braintrust's eval of coding agents found that agentic search and vector search reached the same accuracy, but vector...

The next stage of AI agent development is not better models or harnesses but 'agent recipes' that encode a maker's...

Replicating the IFScale benchmark shows the old 200-instruction ceiling is obsolete: today's frontier models hold...

DoorDash's GenAI platform team built a self-serve evaluation platform that enables non-engineers to run the entire...

Nate Herk shares 12 lessons from 5,000+ hours of building with AI, emphasizing that standing out requires...

SonderMind's AI coach Sonder uses evals-driven development with modular input/output guardrails powered by separate...

Uber's computer vision team built a closed-loop evaluation system for a multimodal agent that enhances food photos...

Arize AI's Signal agent transforms observability data into automated pull requests by combining telemetry traces,...

Evals for AI agents need to evolve from static LLM-as-a-judge to dynamic agent-as-a-judge because traditional evals...

Shipping skills without evals is risky because agents are non-deterministic and skills can degrade performance....

OpenAI's Chief Research Officer Mark Chen discusses the enduring power of scaling laws, the importance of...

AI engineers are in high demand with salaries ranging from $100,000 to over $500,000. A fact-based roadmap to...