Videos

Containment rate — the percentage of conversations handled without a human — is a misleading metric for AI agent...

Langfuse's workshop demonstrates a practical workflow for continuously improving AI agents by combining online...

The central tension in AI-assisted development is that generation is cheap but evaluation is expensive, and the...

Static evals and benchmarks create a 'benchmark illusion' — they don't reflect real customer usage. Amazon AGI Lab's...

Existing LLM judges are confidently wrong, inflating agent success rates by nearly 2x (e.g., 74% vs 38% actual). A...

Weights & Biases' Arya agent uses its own production traces and offline evaluations to generate new tasks and prompt...

Spotify's Large Taste Model, used daily by a quarter of US premium subscribers, shifts personalization from ranking...

Building agents on document intelligence requires decomposing the parsing problem: use traditional computer vision...

1 in 20 production clinical AI notes carry serious errors that could cause significant harm, according to the...

Abridge has moved from clinical documentation to clinical intelligence by using AI to process medical conversations....

Replay agents—blind scripts that replay recorded successful trajectories—can match or beat frontier models on...

Nubank ships AI agents 20× faster by using simulated eval data instead of waiting on production traces. Generating...

Every company needs a private benchmark to reliably evaluate, release, and improve AI agents, moving beyond...

Evaluating AI-generated video quality is harder than generating the video itself. Character.ai built a fast, small...

Agent development is more like machine learning than traditional software engineering, requiring empirical...

Andon Labs created Vending-Bench, a long-horizon evaluation benchmark where AI agents run a simulated vending...

The AI Engineer World's Fair 2026 highlighted that the key to effective AI systems is not just the model but the...

Rachel Lee Neighbors argues that developers can drastically cut costs, improve latency, and enhance security by...

Sandipan Bhaumik from Databricks presents a five-pillar framework for deploying AI agents at enterprise scale,...