

Unconference: Context Engineering in Production
London has one of Europe's most active AI engineering communities, and this is a chance to get in a room with a slice of it. An evening of technical discussion for people building production AI systems, over drinks at Balderton's offices in the heart of the city.
Powered by Haystack (open-source AI orchestration framework) and NVIDIA Nemotron™, the sessions are shaped by what you're actually building, your experience, and your challenges in context engineering.
🎯 What Is Context Engineering?
Context engineering is the practice of deliberately designing the information, tools, and memory that an AI system can access at runtime to reliably complete real tasks.
The way you design your context layer directly impacts cost, performance, and maintenance of your system.
Some example topics we'll discuss:
Human-in-the-loop, guardrails, and security of agentic systems
MCP servers running in production
The power of multimodal LLMs managing multimodal context
Performance/cost tradeoffs of local models in agentic settings
Ways to optimize agent context, tool search, and multi-agent architectures
👥 Who is This Event For?
This event is for builders and decision makers working on real-world AI systems, including:
AI/ML practitioners and engineers
Product managers and tech leads
Founders and engineering managers
Innovation leads and decision makers exploring AI adoption
The goal is to share experiences, ask questions, and learn from others who are building or enabling real-world AI systems.
🧠 Unconference Event Format
This event follows the unconference format. We’ll form discussion groups around context engineering topics shaped by your input during registration, so the agenda reflects what matters most to you.
Bring your questions, share your learnings, or simply listen in and learn from others in the field.
🗓️ Agenda
18:00 - 18:30 Arrival & Welcome Drinks 🥙🍹
18:30 – 18:45 Opening Remarks
18:45 – 19:45 Unconference Sessions
19:45 – 20:30 Wrap-Up & Networking
Use the "Contact the Host" feature on Luma if you have any questions!