Insights
Why AI Coding Agents Need a Context Graph, Not Better Search
In this blog, our Founding AI Engineer explains why AI coding agents need context graphs to write better code (and not just better search). Context graphs connects code, tests, configuration, issues, changes and other engineering decisions - not replacing search, but making it more useful for the agent.
8 Things I Tell AI Review Agents to Look For
"An AI reviewer that has not been told what to look for will review like a generic one." Read Elena's breakdown of the eight things she puts in every AI pull request reviewer's brief, drawn from the review bots she has built.
AI Agent Performance Metrics Start Before the Agent Is Built
Explore how and why AI performance metrics need to be defined and agreed before the agent is built, by WeBuild-AI Principal AI Engineer, Stylianos.
An AI Operating Model Framework That Puts Decision Rights Close to the Work
How do you build an AI operating model framework that ensures decisions are taken by subject matter experts, close to the source of the work? This blog explores the problem with AI-native software development and the speed of delivery, and how to tackle the new blocker of piled up tickets that never reach production.
Almost Right. The Hidden Cost of Code That Passes Every Check
"Suddenly I am a full-time code reviewer." Read Elena's full breakdown of how AI-generated code can pass every check and still be wrong, including the five patterns she now looks for in every diff.
Introducing Deliberate AI: The Method That Gets Enterprise AI into Production
Taking inspiration from The Phoenix Project, we tell the story of Marchmont Group, a fictional enterprise with a hundred and forty-two AI use cases and nothing in production, and introduce Deliberate AI, the methodology we built to close the enterprise AI success gap.
Building the Foundations for a Successful AI Operating Model
How to build an AI operating model that actually delivers: focus investment on two or three high-value workflows, centralise orchestration, establish governance before scaling, design for human-AI collaboration, and plan the talent bridge between internal teams and external partners.
Build Foundational Enterprise AI Using Spec-Driven Development and Architecture Decision Records
From agile and waterfall methodologies to AI-native software development lifecycles - how to standardise spec-driven approaches to build AI-ready enterprises.
10 Steps to Scaling AI Coding Assistants in Your Dev Team
Using AI coding assistants can dramatically increase speed of development, but there’s still bottlenecks that will inhibit delivery. Read our 10 steps to avoid a backlog of unreviewed work that’s never shipped.
Five Workflow Patterns to Multiply Your Development Capacity with AI Coding Assistants
Multiply your software development capacity with AI coding assistants - here’s 5 workflows to get you started
Why your SDLC is slowing down AI delivery (and what to do about it)
Four changes that will adapt your SDLC to enable AI delivery, reduce bottlenecks and increase experimentation
Aligning Spec-Driven Development and Context Engineering For 2026
Are spec-driven development (SDD) and context engineering competing, or complementary - and how do we see that partnership working for 2026?
The SDLC in the Age of Agents: When Everything Happens at Once
How has the software development lifecycle changed in the age of AI agents? Read on to find out
The Context Switching Tax: Here's How To Avoid The Tax Using AI
Enterprise businesses often have fragmented systems with disparate information, and rely on highly skilled engineers to be information repositories. No more - read on to learn about how Model Context Protocol enables context switching at scale.
Why (and why not) train a language model from scratch
Learn about why (and why not to) train a language model from scratch - plus, what would be required to implement in practice










