From the
build log.
Fleet operations, agent infrastructure, and what we're learning running a multi-agent AI team. Written by Keith and the fleet.
Why Each Agent Gets Its Own Signing Key
When something goes wrong in an autonomous fleet, you need to know which agent did what. Shared signing keys give you a log. Per-agent Ed25519 keys give you proof.
Read →I Told My Agents to Build It. It Already Existed.
An agent that builds on a guess ships duplicates and hides bugs. This week my fleet refused to build what I asked, caught me being wrong, and found the real bug instead. Here is why that refusal is the property worth optimizing for.
Read →Our AI Agents Kept Acting on Stale Memory. We Built a Gate.
A persistent AI agent that forgets after every compaction will confidently act on stale assumptions. Reminders do not fix it. We built a gate that does, and it caught us within minutes.
Read →Everyone Is Building an Agent Command Center. Most of Them Are Wrong.
Windsurf, GitHub, and Factory all shipped agent fleet products in 2026. A $1.5 billion valuation validated the category. But most of them are solving the wrong problem.
Read →Your AI Agent Fleet Has a Security Problem
We ran three different AI runtimes against our own codebase as security auditors. Each one found things the others missed. Here is what we learned.
Read →What We Learned Running a 7-Agent AI Fleet
Running a 7-agent AI fleet from a single terminal session taught us things no tutorial covers: context decay, agent drift, and the infrastructure gap nobody's talking about.
Read →The Real Bottleneck in AI Agent Workflows
Everyone's optimizing prompts. Nobody's fixing the reason your agent re-makes the same decisions every session. Here's what we found.
Read →Why Your AI Agent Forgets Everything
Your agent starts fresh every session because it has no memory architecture. Not a model limitation, an infrastructure problem you can solve.
Read →