Jul 23, 2026

Learned Execution Graphs for Anomaly Detection & Drift in APIs — Ritvik Pandya, JP Morgan Chase

Ritvik Pandya from JP Morgan introduces 'learn execution graphs'—short-lived DAGs representing API request processing—to detect anomalies and drift in high-throughput systems. This approach localizes performance issues to exact nodes, identifies skipped or reordered steps, and differentiates between transient anomalies and fundamental system drift (structural, volume, or behavioral). It leverages per-client baselines and OpenTelemetry data to reduce mean time to discovery (MTTD) from hours to seconds, enhancing system reliability and observability.

Jul 21, 2026

Your agent architecture has a half-life of 6 months — Dan Farrelly, CTO, Inngest

Dan Farrelly, CTO of Inngest, addresses the rapid obsolescence of AI agent architectures (a 6-month half-life) caused by fast-evolving models and frameworks. He proposes a solution: decouple agent systems into three conceptual layers (Execution, Context, Compute) and prioritize a stable, durable Execution Layer. This 'brain' layer, responsible for flow, state, and retries, offers resumability, flexible invocation patterns, and comprehensive observability, allowing the 'knowledge' and 'hands' layers to change frequently without necessitating full architectural rewrites.

Jul 20, 2026

Sandboxing, Agent Harnesses, and Agent Teamwork

Shahram Anver, CEO of Cleric, details how AI agents for SRE are evolving beyond fast triage to continuous learning and operational memory. He discusses Cleric's architectural shifts, from complex early designs to simpler, sandboxed query agents, and the unique challenges SRE agents face in diverse production environments. A core focus is on human-agent interaction, redefining roles as managers overseeing agents, and how agents learn from unstructured data like Slack to build robust, actionable knowledge for autonomous, self-healing infrastructure. The discussion also touches on the future of software, differentiating between durable systems and rapidly developed "skills" or "vibe-coded" solutions.

Jul 18, 2026

Your Agents Need a Save Button - Hamza Tahir, ZenML

Most AI agents lack a "save button" for persistent state, making debugging and optimization challenging. This talk introduces the concept of a durable runtime with checkpointing, allowing developers to replay agent executions, perform "what-if" analyses (e.g., swapping models, mocking tools), and conduct cohort-based evaluations using production data. The open-source tool Kitaru is demonstrated as a solution to build, debug, and improve agents at scale by capturing full execution state, not just traces.

Jul 16, 2026

Has AI Finally Cracked Time Series Forecasting?

Ameet Talwalkar, CMU professor and Datadog's Chief Scientist, traces the journey of time series foundation models from early skepticism to their current impact. He details Datadog's Toto V1 and V2, highlighting breakthroughs in zero-shot performance, scaling, and the crucial role of data mix. The discussion extends to the vision of 'world models' for observability, integrating diverse data for self-healing software systems, and concludes with insights on open-weights models and AI's transformative effect on computer science and academic research.

Jul 12, 2026

RLM: Recursive Language Models for Large Codebases - Shashi, Superagentic AI

This talk introduces Recursive Language Models (RLM) as a solution for coding agents struggling with large codebases. RLM externalizes context management into a programmable REPL, allowing the model to write code, inspect the repository, and recursively delegate sub-questions via `llm_query` to curate relevant context. The speaker demonstrates `RLM Code`, an independent implementation, showcasing its operational loop, observability features, and practical applications for AI engineers dealing with complex software projects.