A friend in a regulated industry recently described their AI governance with complete confidence: "A human approves every output."
I asked how many outputs a day. About four thousand. I asked how long each approval takes. A pause. "A few seconds."
That is not a safety system. It is a queue with a person sitting in front of it.
The interesting question in agentic engineering stopped being what do I prompt months ago. These days it's a quieter, more nervous one: how much rope do I hand this thing, and what do I need back before I can walk away from it?
I've been keeping a rough ladder in my head for that — low end, it just suggests and I decide; high end, it runs on its own and only surfaces the decisions that actually need me. It's a useful ladder. It's also been quietly lying to me, and it took a bad week to see how.
The problem, stated plainly: you cannot trust an agent you cannot constrain, ground, measure, or reconstruct — and "trust me" is not an architecture. A model emits tokens. Everything that decides whether those tokens are safe to act on in production lives in the code around it.
The last Agentry post made that pitch. This one opens the hood — every pillar, in the weeds: the loop, the policy engine, identity, the audit chain, grounding, fleets, evals, and the one-dependency bet that holds it all together.
In the last post I reviewed "a toolkit I'd been building." This is that toolkit — and the opinions baked into it.
The pitch in one line: a model is one component; everything that makes it safe and useful in production lives in the harness around it. Agentry is that harness — governed, grounded, evaluated — with one property I care about a lot: it can prove what it did.