AI Agents & Identity
Essays on running AI agents in production: non-human identity, credential governance, control-plane gaps, and when a multi-agent swarm is actually justified.
Notes on operating AI agents for real work: non-human identity and credential governance, the control-plane gap when a prompt becomes an approval, why we built AgentOS, and when a multi-agent swarm is justified at all. The bar throughout: the second agent should be cheap, and the fiftieth should be boring.
10 posts, newest first
Your Prompt Is the Approval. That's the Gap.
An MCP connector executes writes with no approval screen — your prompt becomes the one boundary nobody governed. That missing gate is a control-plane gap.
Prove You Need the Agent Before the Swarm
Token spend explained ~80% of variance in multi-agent runs; most "AI failures" are provisioning mistakes. Treat a swarm as segregation of duties.
Shadow AI: Your "Personal Tool" Is Production
A coding agent stands up a data-touching tool in an afternoon. The moment it needs a login or gets shared, it's a production system nobody reviewed.
The Second Agent Cheap, the Fiftieth Boring
Build cost was never the constraint in a regulated shop — agent #50 hits the same security review as agent #1. Make identity and action gates reusable.
Why We Built AgentOS
One model scored 78% in one agent harness and 42% in another. In regulated fintech the harness is where governance lives, so we built our own: AgentOS.
Nobody Is Governing Your Agents' Credentials
Your agents already outnumber your people, they can authenticate but not prove they're authorized, and that's the gap SOC 2 and HIPAA were never built to close.
The Control Plane Is the Job
Standing up an agent takes an afternoon; the control plane that lets it touch production safely is the actual engineering work, and almost nobody shows it.
Make Your Enterprise Agent-Readable First
Everyone is racing to buy agents; almost no one builds the substrate that lets them act safely. The productivity is real — so is the blast radius.
Agent Safety: Engineer the Blast Radius
Most agent "safety" is a politely worded request to a model that need not honor it. The only controls that count still hold after the model goes wrong.
Agent Onboarding Was Easy. Offboarding Isn't.
Every team shipped an agent in a weekend. Almost none can say how it gets fired, what credentials it still holds, or who would notice if it went rogue.