Microsoft Research introduces MagenticLite, an agentic framework powered by two new small, open-weight models: Magentic Orchestrator for planning and coding, and Fara-1.5 for browser automation. The talk details the novel synthetic data generation techniques and training strategies used to achieve state-of-the-art performance in small models, enabling them to compete with much larger ones.
Agentic AI failures are often predictable system design flaws, not random hallucinations. This summary explores the top three failure modes—infinite loops, hallucinated planning, and unsafe tool use—and provides practical strategies for designing more reliable and robust AI agents.
Vincent Koc argues that static benchmarks are failing in the era of adaptive AI. He proposes a shift from static testing to 'malleable evals,' where agents self-optimize and curate their own test suites based on user intent and production data, treating evaluation as a living, evolving system.
Varant Zanoyan, original author of the Chronon feature platform, introduces 'agentic experimentation'—a pattern where AI agents improve high-stakes ML systems without making live decisions. He explains how Chronon solves key challenges like infrastructure sprawl, safety, and reproducibility through a semantic API, branch-based isolation, and compute reuse, enabling agents to safely create production-ready pipelines for human review.
A deep dive into building production-ready, stateless, and scalable LLM agents by leveraging the Model Context Protocol (MCP) and Strands SDK on AWS Lambda. The session demonstrates how to expose real-world functionality to language models, moving beyond mere reasoning to tangible action.
Martin Keen explains that context, not model intelligence, is the biggest bottleneck in AI. He introduces Context Engineering, its four pillars (Connected Access, Knowledge Layer, Precision Retrieval, Runtime Governance), and advanced techniques like GraphRAG to build more reliable, context-aware AI systems.