
AUTHOR
Patrick Debois
Patrick is a pioneer, credited with coining the term DevOps, co-authoring the DevOps Handbook, and launching the very first DevOpsDays back in 2009. Since then, he’s been shaping the tech industry and brings depth across development, security, operations, and GenAI.
Articles

Article
Your Software Factory: Dream Factory or Treadmill?
Your agents ship more code each week. Yet the same questions return in Slack, the migration never quite finishes, and every new engineer discovers the same gaps in the setup guide. The factory is b...

Article
Who owns the cost of the AI software factory?
The article explores managing AI software factory costs, emphasizing visibility, ownership, and accountability to optimize budgets and improve workflow efficiency.

Article
Review Isn’t the Bottleneck. Risk Is.
The article explores how risk management, not review processes, is the true bottleneck in AI software development, emphasizing the need for systems to prevent mistakes and manage outcomes.

Article
How Open Is Your Software Factory?
Explore the importance of software factory openness, focusing on retaining business knowledge and understanding beyond code generation for strategic advantage.

Article
Engineering a Context-Driven Software Factory
Explore how context-driven software factories enable agents to handle complex tasks, requiring engineering practices to ensure reliable decision-making and automation.

Article
AI DevCon NYC: From Coding Agents to Software Factories
Curating a conference is an interesting way to see where an industry is heading, because the program tends to reveal which questions have already become accepted and which ones people are only star...

Article
The State of the AI Coding Stack: Agent Skills, Harnesses, and Enablement at AI Native DevCon London 2026
AI Native DevCon London 2026 explored the evolving AI coding stack, focusing on agent skills, context development, and governance in AI-native software processes.

Article
Context Maturity for AI Coding Teams
Explore the maturity path for AI coding teams focusing on context management, toolchain awareness, and organizational roles to enhance agent productivity.

Article
CI/CD for Context in Agentic Coding: Same Pipeline, Different Rules
Explore how CI/CD principles apply to managing context in AI coding agents, focusing on evals as tests and the challenges of integrating them into development pipelines.

Article
The Context Flywheel: Why the Best AI Coding Teams Will Win on Context
The Context Flywheel explores how iterative context development in AI coding teams enhances agent output, expertise, team learning, and organizational alignment.

Article
The Context Development Lifecycle: Optimizing Context for AI Coding Agents
The Context Development Lifecycle focuses on optimizing context for AI coding agents, highlighting the shift from code writing to context understanding in software development.

Product
Introducing Task Evals: Measure Whether Your Skills Actually Work
Today we’re launching Task Evals: a built-in way to measure whether a skill is actually steering agent behaviour. Skills can be well written and still drift as models and surrounding context change. Task evals compare outcomes with and without a skill, making it clear when it’s helping, doing nothing, or working against you.














