Coding agent adoption for engineering teams
For teams adopting coding agents, whether you start with one tool in one team or bring several tools and teams together, and want a rollout you can operate yourselves.
Engineering consulting
Public projects
These are the founder's public projects. They show how we approach agent tooling. They aren't customer case studies.
Discuss your setupRunmill
Runmill takes an eligible Linear issue and runs Claude Code or Codex in an isolated workspace. The exact candidate commit must pass required checks and a fresh-context review before a GitHub pull request and CI. Deterministic code, not the agent, decides pushes, pull requests and merges.
- Status: developer preview
- Automatic merge is experimental
ctxlane
ctxlane keeps separate Claude and Codex profile states and directory contexts. Static secrets for its wrapper go in the native OS credential store. The official vendor CLIs handle authentication and model requests. It is standalone and doesn't integrate with Runmill.
- Tested against simulated vendor CLIs
- Not yet qualified with real accounts, keyrings or billing
Why they're here
They show the kind of engineering we do. Read the code and judge for yourself.
Questions
Can we use these in production?
Check the current documentation, code, tests and controls against your own requirements. Runmill is a developer preview and its automatic merge is experimental. ctxlane has only been tested against simulated CLIs and isn't yet qualified with real accounts, keyrings or billing.
Are these used by customers?
They aren't presented as customer work.
Related services
Coding agent evaluations on your repositories
Public benchmarks say little about how an agent performs on your code. We help you evaluate models and harness changes on tasks from your own repositories.
LLM cost optimization for coding agents
We help you work out where your coding agent and LLM spend goes, then implement the changes that hold up when tested against quality.