Join us at Google for an evening of AI conversations and demos. Whether you're building with LLMs, experimenting with prompts, or just AI-curious, pull up and hang out with other folks doing interesting things in the space. We'll have lightning talks, plenty of time to chat, and the usual good vibes.

Talk: Async Agents in Production: Failure Modes and Fixes

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.

Meryem Arik is the co-founder and CEO of Doubleword, where she works on large-scale LLM inference and production AI systems. She studied theoretical physics and philosophy at the University of Oxford. Meryem is a frequent conference speaker, including a TEDx speaker and a four-time highly rated speaker at QCon conferences. She was named to the Forbes 30 Under 30 list for her work in AI infrastructure.

Talk: Lock Claude Down, Set It Free

Every time Claude Code reads a webpage, it might also be reading instructions from an attacker. The standard defence is permission prompts. But click allow 85 times and you stop reading - and then the 86th one exfiltrates your SSH keys.

Lockbox solves this structurally. It tracks what Claude has been exposed to and restricts what it can do next. Read a webpage? Fine, but now you can't git push. Need to push? A clean sub agent handles it, with one high level approval that actually matters. More freedom through better constraints. This talk introduces the tool and shows you how to use it, with a live demo.

Chris Parsons is the founder and co-organiser of LLM London.

More talks to come...

This event is hosted and sponsored by Google UK

Location

6 Pancras Sq

London N1C 4AG, UK

Presented by

LLM London

Building the future with AI

Hosted By

144 Going

AI