Async Agents in Production: Failure Modes and Fixes — Seb Ringrose | AI in Production 2026

Long-running async agents fail in ways short-lived ones don't. The most common failure modes — and the design patterns that keep errors and token costs bounded in production. Presented by Seb Ringrose (Doubleword) at AI in Production 2026 — The Catalyst, Newcastle, 5 June 2026. ABOUT THE TALK As models improve, we are starting to build long-running, asynchronous agents such as deep research agents and browser agents that can execute multi-step workflows autonomously. These systems unlock new use cases, but they fail in ways that short-lived agents do not. The longer an agent runs, the more early mistakes compound, and the more token usage grows through extended reasoning, retries, and tool calls. Patterns that work for request-response agents often break down, leading to unreliable behaviour and unpredictable costs. This talk is aimed at use case developers, with secondary relevance for platform engineers. It covers the most common failure modes in async agents and practical design patterns for reducing error compounding and keeping token costs bounded in production. SPEAKER Seb Ringrose — Doubleword: https://www.doubleword.ai/ LinkedIn:   / sejori   ——————————————— AI in Production is Jumping Rivers' conference for data scientists, ML engineers and AI practitioners building and deploying AI & ML in the real world. The inaugural event was held at The Catalyst, Newcastle Helix, on 4–5 June 2026. 🎟 Event & full programme: https://ai-in-production-2026.jumping... ▶ More talks from the conference:    / @jumping-rivers   📑 Full playlist — every AIP 2026 talk:    • AI In Production 2026   🌊 Organised by Jumping Rivers: https://www.jumpingrivers.com/ With thanks to our sponsors — Databricks, Posit, the Royal Statistical Society, Chapman & Hall/CRC, and the National Innovation Centre for Data. Community partner: DevITJobs.uk. #AIinProduction #AIP2026 #MachineLearning #LLMs #AIEngineering