From the Studio
Code Carvers Field Notes
Practical notes on AI operationalization, agent systems, platform engineering, governance, cost, security, and the operational decisions that turn a pilot into production.
October 10, 2026 / 10 min read
AI Made Output Cheap. Attention Is Still Expensive.
AI makes implementation cheaper. Choosing what to build, reviewing what comes back, and protecting each other's attention still take work.
October 2, 2026 / 9 min read
Getting your repo ready for background coding agents
What it took to run background coding agents in a monorepo with hundreds of Lambdas: a usable local environment, isolated worktrees, meaningful checks, and smaller tasks.
September 13, 2026 / 19 min read
The last level of coding-agent autonomy is a harness problem
Humans are reviewing less code, AI reviewers are filling the gap, and the teams that let agents merge unattended got there through harness work. Here is what your repo needs and how to start today.
September 6, 2026 / 8 min read
The control plane behind production AI agents
A practical control-plane design for agent identity, permission, delegation, isolation, auditability, containment, shutdown, and risk-based human approval.
July 5, 2026 / 9 min read
MoA, Agent Teams, and the missing piece in coding-agent workflows
MoA looks like a model-diversity story at first. In coding-agent workflows, the stronger lesson may be role design, stopping conditions, and verification loops.