Work with me
I help AI infra teams (agents infra: sandboxes, agent VMs, computer-use and browser infra, and agent evals) get understood by developers.
What I do
01
Technical teardowns and benchmarks
An independent, reproducible look at your product next to the alternatives. Open method, raw data, and an honest write-up developers will actually trust.
02
Docs, tutorials and launch posts
Getting-started guides, migration guides and launch write-ups that are tested end to end before they ship.
03
Contract AI engineering
Hands-on builds for agents, RAG and evals: harnesses, sandboxed tool use, eval pipelines and the deployment around them.
Proof
- Sandbox time to first command: an open benchmark across agent sandbox providers, with raw data for every run.
- How long until a fresh sandbox runs your first command?
How it works
- A short call about what you want developers to understand.
- A fixed-scope proposal with a clear deliverable and price.
- Delivered in 1 to 2 weeks.
Contact
DM @buildersbuildev on X.