CoreWeave's Fully Connected 2026 Day 1 keynote centers on the AI loop of run, observe, curate, improve and evaluate, and the launch of CoreWeave Forge. It covers production agent operations, agent observability and RL rollouts, Vera Rubin NVL72 and the Vera CPU, and enterprise evaluation practices from Capital One, Caterpillar and Cognition.
Exa's Jon details how their company maintains a massive, continuously updated semantic index of 100 billion pages to serve AI agents. The talk covers Exa's unique incremental indexing system, a custom data processing framework called "Skeleton" that handles 100,000 pages per second, and "Pythia," an elastic, cost-aware GPU orchestration system for managing both real-time ingestion and large-scale index re-embeddings.
A bank's AI demo works but cannot ship due to non-engineering problems like security, data ownership, and risk approval. Paden Gayle outlines a method focusing on early stakeholder discovery, iterative workflow scoping, gradual autonomy, and a comprehensive evidence pack to build AI systems with a credible path to production, emphasizing that "discovery is the engineering."
Charles Frye explains the architecture, performance engineering, and operational challenges of LLM inference engines. He dissects workload types, core components like schedulers and kernel backends, and advanced techniques such as KV caching, CUDA graphs, and speculative decoding, concluding with essential strategies for observability and debugging in production environments.
This talk by Jess Wang from Braintrust delves into the critical importance of evaluations (evals) in AI development, moving beyond subjective "vibes" to data-driven decision-making. She breaks down the four core components of an eval—dataset, task, scoring, and experiments—and illustrates the continuous improvement "eval flywheel" integrating observability. The central experiment compares agentic search against vector search for a coding agent tasked with finding buggy code in Microsoft's TypeScript Go repo. While both methods achieved identical accuracy, vector search proved four times more expensive due to its inability to capture surrounding context within code chunks, leading to excessive, inefficient searches. Wang concludes with practical caveats and best practices for conducting effective LLM evals.
Abi Aryan discusses the shift from MLOps to LLMOps, framing generative AI deployment as a distributed systems challenge. She highlights the critical role of FinOps due to high model costs, the need for custom tooling over generic agent frameworks, and the importance of a 'decision layer' for agent autonomy. Observability is re-conceptualized as anomaly detection, and she points to dynamic RL environments and strong data engineering as future research priorities and essential skills for AI engineers.