9 articles in How we build
CODEOWNERS, blame, and branch protection were built around named humans with reputation. When the committer becomes an agent, the trust scaffolding stays standing on a foundation that quietly disappeared — and the load migrates to a single reviewer's signature.
Your engineering agent reviews PRs, writes tests, and ships code. Nobody can tell you whether it is better than rubber-stamping. Without evals on the agent itself, you are flying blind on the tool that is making 40% of your engineering decisions.
A PM and an engineer sit down with four colors of sticky notes. Sixty minutes later they have surfaced every business rule, every edge case, and every unanswered question — and produced acceptance tests an AI agent can build against. No prose. No translation layer. No "the AI guessed wrong" post-mortem.
Most teams deploy agents at stage five speed on stage two or three foundations. AI amplifies whatever it's applied to — strong process gets faster, broken process gets more broken, faster. The question before expanding agent use is not whether. It's where your codebase actually sits.
When an AI agent works on your codebase, your test suite is the only artifact of intent it consistently sees. Tickets, Notion pages, and Slack threads do not enter the loop. If your tests describe what the system should do, the agent is constrained. If they only describe what the code already does, the agent ships whatever it generated.
Best practices documents fail because compliance requires humans to consistently remember and apply them. Quality gates work because they remove humans from the enforcement loop entirely.
Most teams treat engineering quality reactively — ship fast, catch problems in production, fix when it hurts. That cycle keeps you busy without making you better. Prevention, Detection, and Correction form a closed loop where each phase reduces the work the next must do.
A team of two junior engineers and one mid-level engineer shipped 200,000 lines of production-grade code for an Industrial IoT platform — achieving elite DORA metrics and an 8.8 code health score from day one. No seniors. No rewrites. Here's how Prevention made it possible.
A new framework argues that coding agents need external "harnesses" — feedforward guides and feedback sensors — to produce reliable code. We agree. We also built one. Here's how theory maps to a production system, concept by concept.