AI Native Engineers London
Practical AI for Software Engineers - dev tools in SDLC, core patterns for LLM implementation
AI for Engineers London is a community for software engineers who want to harness AI to build better software, faster.
We focus on the engineering side of AI, not ML/data science, sharing battle-tested approaches, practical tools, and proven patterns that transform how you write, test, deploy, and maintain code today.
Join us for monthly meetups featuring live demos, case studies from London tech companies.
For collaborations, reach events@gitnation.org
Topics covered:
🛠️ AI-Enhanced Development & Delivery
Development Acceleration
Code generation with Claude Code, GitHub Copilot, Cursor, and emerging tools Automated code reviews, refactoring, and documentation generation Test generation and intelligent debugging assistance Building with MCP servers, LangGraph, CrewAI, and agent orchestration frameworks Smart monitoring, alerting, and root cause analysis Self-healing systems and automated incident response 🔧 Practical LLM Integration PatternsLearn proven patterns for adding AI capabilities to your applications without complexity:
Core Integration Patterns
RAG (Retrieval-Augmented Generation): Connect LLMs to your databases and documentation to answer questions using your own data — no model training required LLM optimizations Prompt Templates & Chaining: Structure prompts for consistent outputs and chain multiple AI calls for complex tasks Input/Output Validation: Add guardrails to ensure AI responses meet your requirements — from JSON schemas to content filteringAnd other topics within core theme of the group
Building a UI That Builds Itself
What if an AI agent could customize its own UI outside the chat and update it on the fly? As humans, some tasks that we work on are better done visually than in text format. That's why I started this experiment, where I give an agent a skill and teach it how to work in a highly visual workspace it can extend and update with custom UIs. I'll walk you through how we designed a skill, a CLI, and a front-end app that work in tandem to make it possible. How we spent weeks figuring out the best and most minimal design system an agent can use to generate "slop-free" designs. The project is completely open-sourced and available on https://moi.computer/
Alexey Taktarov
Stop Paying for Frontier Models
Most of use reach for a frontier model by default and pay for it on every call, in latency, in energy, in cash, and in everything that leaves their stack. For most of those calls, a small local model would do the job.
RL Nabors, former Meta/React core team member and AWS alum, covers the vocabulary you need to reason about model performance (capability evals, golden datasets, LLM-as-judge) and walks through real cases: a local agentic harness replacing a frontier call, an in-browser moderation classifier defended with production-trace evals, and a generative summarization feature where the rubric turns out to be harder than the model. You'll leave with a framework for deciding when to choose large and off-prem or small and local models, and how to measure your way to the answer instead of guessing.
You will learn:
The vocabulary to reason about model performance (capability evals, golden datasets, LLM-as-judge). A framework for deciding when a small or local model can replace a frontier one and when it can't. A repeatable process for building capability evals from your own production traces, not someone else's benchmark. Working examples of using eval results to iterate on prompts and ship with confidence instead of vibes.
Rachel Nabors
The Worktree Swarm: 2 Humans, N Agents, 8 PRs, 1 Day
A walkthrough of a real session where two developers and their AI agent teams collaborated on a complex architectural change — going
from a rough spec to 8 PRs, 4,500 lines of code, and a clean task board in a single day.
The talk covers how we used git worktrees as a shared context surface between two developers' Claude Code agents, spawned specialist
subagents (including a Redis expert that caught two critical production bugs during design review), ran parallel implementation
across multiple branches, and coordinated via a dedicated agent that polled for commits and monitored Slack and CI.
The focus is on the collaboration model — not the technical feature itself — and what the human's role becomes when AI agents can
read, write, test, and coordinate autonomously.
Sam Winstanley
Clade Code for the entire stack from monorepo to multi-region cloud
Valera Iatsko, Google https://github.com/viatsko
Valera Iatsko
How Figma uses coder.com and autonomous agents
Daniel Büchele, Figma, https://www.linkedin.com/in/danielbuechele/
Daniel BücheleAI Native Engineers London
Practical AI for Software Engineers - dev tools in SDLC, core patterns for LLM implementation
AI for Engineers London is a community for software engineers who want to harness AI to build better software, faster.
We focus on the engineering side of AI, not ML/data science, sharing battle-tested approaches, practical tools, and proven patterns that transform how you write, test, deploy, and maintain code today.
Join us for monthly meetups featuring live demos, case studies from London tech companies.
For collaborations, reach events@gitnation.org
Topics covered:
🛠️ AI-Enhanced Development & Delivery
Development Acceleration
Code generation with Claude Code, GitHub Copilot, Cursor, and emerging tools Automated code reviews, refactoring, and documentation generation Test generation and intelligent debugging assistance Building with MCP servers, LangGraph, CrewAI, and agent orchestration frameworks Smart monitoring, alerting, and root cause analysis Self-healing systems and automated incident response 🔧 Practical LLM Integration PatternsLearn proven patterns for adding AI capabilities to your applications without complexity:
Core Integration Patterns
RAG (Retrieval-Augmented Generation): Connect LLMs to your databases and documentation to answer questions using your own data — no model training required LLM optimizations Prompt Templates & Chaining: Structure prompts for consistent outputs and chain multiple AI calls for complex tasks Input/Output Validation: Add guardrails to ensure AI responses meet your requirements — from JSON schemas to content filteringAnd other topics within core theme of the group
Building a UI That Builds Itself
What if an AI agent could customize its own UI outside the chat and update it on the fly? As humans, some tasks that we work on are better done visually than in text format. That's why I started this experiment, where I give an agent a skill and teach it how to work in a highly visual workspace it can extend and update with custom UIs. I'll walk you through how we designed a skill, a CLI, and a front-end app that work in tandem to make it possible. How we spent weeks figuring out the best and most minimal design system an agent can use to generate "slop-free" designs. The project is completely open-sourced and available on https://moi.computer/
Alexey TaktarovStop Paying for Frontier Models
Most of use reach for a frontier model by default and pay for it on every call, in latency, in energy, in cash, and in everything that leaves their stack. For most of those calls, a small local model would do the job.
RL Nabors, former Meta/React core team member and AWS alum, covers the vocabulary you need to reason about model performance (capability evals, golden datasets, LLM-as-judge) and walks through real cases: a local agentic harness replacing a frontier call, an in-browser moderation classifier defended with production-trace evals, and a generative summarization feature where the rubric turns out to be harder than the model. You'll leave with a framework for deciding when to choose large and off-prem or small and local models, and how to measure your way to the answer instead of guessing.
You will learn:
The vocabulary to reason about model performance (capability evals, golden datasets, LLM-as-judge). A framework for deciding when a small or local model can replace a frontier one and when it can't. A repeatable process for building capability evals from your own production traces, not someone else's benchmark. Working examples of using eval results to iterate on prompts and ship with confidence instead of vibes.Rachel NaborsThe Worktree Swarm: 2 Humans, N Agents, 8 PRs, 1 Day
A walkthrough of a real session where two developers and their AI agent teams collaborated on a complex architectural change — going
from a rough spec to 8 PRs, 4,500 lines of code, and a clean task board in a single day.
The talk covers how we used git worktrees as a shared context surface between two developers' Claude Code agents, spawned specialist
subagents (including a Redis expert that caught two critical production bugs during design review), ran parallel implementation
across multiple branches, and coordinated via a dedicated agent that polled for commits and monitored Slack and CI.
The focus is on the collaboration model — not the technical feature itself — and what the human's role becomes when AI agents can
read, write, test, and coordinate autonomously.
Sam WinstanleyClade Code for the entire stack from monorepo to multi-region cloud
Valera Iatsko, Google https://github.com/viatsko
Valera IatskoHow Figma uses coder.com and autonomous agents
Daniel Büchele, Figma, https://www.linkedin.com/in/danielbuechele/
Daniel BücheleGet in touch!
hi@guild.host