Inside Cloudflare's software factory
An AI code reviewer running up to seven specialist agents per merge request across 5,169 repositories, built on the same developer platform Cloudflare ships to customers.
Inside the software factories of leading engineering teams.
How engineering organisations actually use AI agents across the software development lifecycle.
Profiled teams
Inside DoorDash's software factory
Flux, DoorDash's in-house cloud-agent platform, started with one narrow use case, code review, before expanding to 130,000 automated engineering tasks a month; the reviewer it grew from now covers 10,000+ pull requests a week across 56 repositories and can push its own suggested fixes straight back to the PR.
AI-assisted
Inside Ramp's software factory
Four engineers plus one part-time PM built an in-house background agent that now authors 3 of 4 merged pull requests, and gave it the same tool access as a human engineer.
Inside Shopify's software factory
The famous CEO memo wasn't the whole record. Underneath it sits a Slack-native agent coauthoring one in eight merged PRs, a security harness that requires proof by exploit, and a refusal to count AI-authored lines of code.
AI-native
Inside Snap's software factory
A three-part agent pipeline, Casper for background PRs, CodePal for review, Code Search for navigation, on top of a stated claim that more than half of all agent investment goes into guardrails rather than the agents themselves.
Inside Stripe's software factory
One-shot end-to-end coding agents on a forked Goose, gated by a hard two-round CI cap and a shared 500-tool internal MCP server.
AI-native
Inside Uber's software factory
Six platform layers, an agent registry that makes every agent action traceable to a person, and the most honest published account of what AI measurement got wrong.
AI-native
Inside WorkOS's software factory
An in-house code factory that turns tracker issues into human-approved pull requests inside isolated cloud sandboxes, plus an open-source harness that refuses to open a PR without evidence the work was tested.
Inside Zalando's software factory
Agentic engineering across 250+ teams since January 2024, with no mandated tool and a risk classifier that auto-approves a third of pull requests.
AI-assistedSoftware factory patterns 9
Pattern
The internal MCP gateway
What an internal MCP gateway is, why large teams end up building one, and what to look for when deciding on one.
Spend control
How companies bound what an agent is allowed to spend, in dollars, tokens, or iterations, and what to look for when deciding on one.
The background agent
What a background coding agent is, why companies build rather than buy one, and what to look for when deciding on one.
The model router
What a model router is, why large teams route every model request through one layer, and what to look for when deciding on one.
Shared agent context
Why companies treat what an agent knows about the codebase as a versioned artifact, and what to look for when deciding on one.
The quality gate
The checkpoint that decides whether an agent-written change is safe to merge, and what to look for when deciding on one.
Ephemeral environments
Why large teams keep a pool of pre-warmed, disposable sandboxes ready for agent sessions, and what to look for when deciding on one.
The identity layer
How an agent gets its own scoped, revocable identity instead of borrowing a human's, and why this is one of the genuinely contested patterns.
The guardrail layer
Why the most sophisticated teams enforce rules as code an agent can't get past, instead of asking nicely in a prompt.