AI Native Dev London: What Breaks When You Let an Agent Loose on Your Repo

Issue in, PR out: what actually breaks when you automate the dev loop 

Everyone's demoing agents that write code. Almost nobody shows you what breaks when you let one loose on your repo. Two builds, two honest reports, zero hype.

Can't make it to London? We're live streaming the whole thing. Register to watch from anywhere: https://luma.com/c3b1f2yu

Agenda

• 18:00 Venue opens

• 18:30 Talk 1: A Software Factory Build Report: What Worked, What Broke, What I'd Do Again by SImon Maple

• 19:00 Talk 2: Harness Engineering is not new by Carly Richmond

• 19:30 Networking

• 20:30 THE END

A Software Factory Build Report: What Worked, What Broke, What I'd Do Again

In this session I'll present a full, honest account of building an autonomous issue-to-PR factory for my open-source project. I'll cover how I built a factory in layers, the decisions that paid off (versioned review lenses, deterministic gates), and the ones that cost me. I'll show where autonomy earned trust and where a human still has to step in, and how the developer's job quietly shifted from writing code to architecting changes the pipeline can execute via issues. The goal is to give you a realistic build plan, with potholes marked, so you can follow the same route with fewer scars.

Simon Maple, Developer Relations at Tessl

Simon Maple is the Head of Developer Relations at Tessl, and AI Native Dev co-host. Previously, Simon was the Field CTO, and VP Developer Relations at Snyk, ZeroTurnaround, and IBM. He became a Java Champion in 2014, JavaOne Rockstar speaker in 2014 and 2017, Duke’s Choice award winner, Virtual JUG founder and organiser, and London Java Community co-leader.

Harness Engineering is not new

Prompt engineering. Context engineering. And now Harness engineering. We love acronyms in the AI ecosystem. Yet much of the differences between context and harness engineering lies in practices, with a few tweaks, that we would consider traditional software engineering best practices. Join me as I walk through harness engineering and show what is a changing discipline, such as aspects of prompt and context engineering, and what is a traditional best practice in a different guise such as CI/CD pipelines, testing, monitoring and evaluation.

Carly Richmond, Developer Advocate Lead at Elastic

Carly is Developer Advocate Lead at Elastic, based in London, UK. Before joining Elastic in 2022, she spent over 10 years working as a technologist at a large investment bank, specialising in front-end web development and agility. She is a UI developer, who occasionally dabbles in writing backend services, a speaker and a regular blogger.

She enjoys cooking, photography, drinking tea, and chasing after her young son in her spare time.

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