Context is King: Engineering Reliable AI Coding Systems
Join the AI Native Dev community in London for an evening focused on one of the hardest engineering problems in AI-native software development: giving coding agents the right context.
As AI systems move beyond autocomplete into code review, testing, architecture decisions, and autonomous workflows, context has become critical infrastructure. How agents interpret repositories, internal libraries, specifications, conventions, and developer intent directly impacts reliability, correctness, and trust.
This meetup explores how engineering teams are building production-grade AI systems around software development workflows. We’ll cover practical strategies for context engineering, AI-powered code review, evaluation systems, model orchestration, and integrating LLMs into real developer infrastructure at scale.
Agenda
18:00 Venue opens
18:30 Talk 1: Context is King by Simon Maple
19:00 Talk 2: AI-Powered Code Review by Serhii Yakovenko
19:30 Networking
20:30 THE END
[Talk 1] Context is King
For AI coding agents, context plays a central role in shaping output quality, consistency, behaviour and style. This session explores context as an engineering concern rather than a prompting detail.
We’ll look at how agents interpret different forms of context, including how their accuracy can be improved when coding against both open-source dependencies, and internal libraries. We'll look at how context, as a specification, can change the behaviour of a coding agent and steer it's decisions, including testing strategies, and project structures. Through practical examples, we’ll show how context influences code generation as well as other important areas, such as code review, from individual PR-level guidance to repo-wide testing.
We’ll also look at what happens when we overwhelm an agent with context and how this will decay, and reduce reliability, and how to overcome this. By the end of the session, you’ll understand how to structure and maintain context so AI agents produce results that align more closely with your code, architecture, and team practices.
Simon Maple, Head of Developer Relations at Tessl
Simon Maple is the Founding Head of Developer Relations at Tessl and former VP of Developer Relations at Snyk, ZeroTurnaround, and IBM; a Java Champion since 2014, JavaOne Rockstar speaker, Duke's Choice award winner, Virtual JUG founder, and London Java Community co-leader.
[Talk 2] AI-Powered Code Review
Every engineering organisation is experimenting with AI coding assistants, but few have built production-grade LLM integrations into their core developer infrastructure. This talk shares real patterns from deploying an AI-powered code review system across a 400+ person engineering organisation (~200 developers) — covering a competitive evaluation of 4 tools across 18 dimensions, building a webhook-based review architecture with slash commands and auto-review, evolving context enrichment from static rules to AI-powered document selection,
managing a 4-model fallback chain on Vertex AI, and measuring impact through a feedback dashboard. Attendees leave with a battle-tested playbook for integrating LLMs into their own engineering workflows — not as toys but as production infrastructure.
Serhii Yakovenko, Software Engineering Manager at M&S
Serhii Yakovenko is a software engineer and AI infrastructure specialist with experience building scalable developer platforms. He has led production-grade LLM integrations for code review and flaky test detection, and developed real-time observability dashboards using Redis within large engineering organizations.
This event is brought to you as part of the AI Native Dev Community. Consider subscribing to the Mailing List, Podcast, and joining our Discord Community