Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The talk identifies a concrete regression in evaluation rigor — from data-science-grounded practices to ad hoc LLM-graded metrics — and maps five specific failure modes that teams building on agents are repeating at scale.
The video demonstrates, with a concrete Terminal Bench result, that harness engineering can deliver large performance gains without any change to the underlying model — making it an accessible optimization path for practitioners who lack access to proprietary model fine-tuning.
Teams building agents with Google ADK gain a path to production-grade managed infrastructure — with persistence, streaming, and tracing — without rebuilding their agent outside the ADK framework.
Developers shipping multi-user agents on LangSmith can now enforce per-user data isolation and role-based permissions with roughly 40 lines of Python, eliminating the need for custom middleware or separate access-control infrastructure.