Talk

LiveDay LDN

Context is the new code: The context development lifecycle

The context that drives AI coding agents has become the primary lever determining what gets built, yet we treat it like we treated infrastructure in 2005: artisanal, unversioned, untested, and invisible.

That has to change. The context development lifecycle (Generate, Evaluate, Distribute, Observe) gives us the stages. The engineering practices that wrap around it include version control, peer review, CI/CD pipelines, and team workflows that make context a shared responsibility rather than individual prompt-craft.

Jun 23, 2026

11:00

BST

Meet the speakers

Patrick Debois
AI Product Engineer, Tessl

The real unlock is the context flywheel. As agents consume context and produce results, every observation feeds back into better context, which produces better results. The teams that get this loop spinning build a compounding advantage that becomes their moat. Those who don’t will keep wondering why their agents feel stuck.

This is not a solved problem. It’s a journey we’ve already started, and if the DevOps transition taught us anything, the teams that figure out the lifecycle first will pull ahead fast.​​​​​​​​​​​​​​​​

Attendees will learn that there is a new cycle next to the software development cycle. It will require its own process and infrastructure to deal with.

It's coming to a platform and enablement team near you!

Register for the
session