Torta Studios Get the guide

Free field guide · Book II

So your agents ship code. Now make that boring.

This field guide is the full story of how we run AI agents as production software: the contract that feeds them, the gate that authorizes them, the failure paths designed for them, and the discipline that lets a security finding dispatch its own fix.

12 chapters Real production system
Get the field guide
web edition + PDF download

The complete guide: the self-healing loop, the day it broke, the work contract, the Health Code, designed failure, verification, observability, memory, the new attack surface, and the 24-question scorecard.

The guide opens right here. We’ll also email it to you, and send you The Proofing Room, our newsletter. One click unsubscribes.

How it starts

The vulnerability fixed itself.

A security scanner finds a vulnerable dependency. Nobody reads the alert, because nobody has to: the finding becomes a validated work order, passes an authorization gate that recognizes a security finding as its own justification, and a sandboxed runner opens the pull request.

The only human in the loop is the one with the most leverage: the reviewer who merges. This guide is everything that makes that loop safe to run.

6
front doors, one work contract
1
authorization gate, fails closed
0
merges an agent can perform
0
jobs allowed to vanish silently
One self-healing loop proves possibility. An operation needs the loop to hold when things go wrong.

The problem this guide solves

Capability is what your agents can do. Operations is what they cannot.

Anyone with an API key can rent the capability. The operation is the part you have to build. If your agents write code, run jobs, or touch production today, run this test against your own setup:

You probably have

capability
  • Agents that write and ship real code
  • Automations wired to your tools
  • Impressive one-off saves to talk about
  • Careful people watching over it all

You probably don’t

operations
  • One gate deciding what agents may change
  • A designed place where failed work lands
  • Checks that catch tests asserting nothing
  • An audit of what agents run automatically

Inside the guide

Twelve chapters. One argument.
01 The fix nobody wrote. A security finding dispatches its own remediation.
02 The day it was not boring. The broken deploy that wrote our rules.
03 Run the kitchen, then leave it. AI Ops defined, and why ours has kitchen names.
04 Six doors. One envelope. The work contract every trigger speaks.
05 The Health Code: who may change what. Who may change what, drawn as one matrix.
06 Every failure gets an address. Dead letters, replay, exactly-once.
07 Never trust the author, even when it is you. Quality gates that ignore who wrote the code.
08 Agents appear in the traces. Observability for the agents themselves.
09 An agent that forgets is a contractor forever. A governed store, and the two-memories war story.
10 Your agents are an attack surface now. The worm that targeted agent config files.
11 What this does not solve. The honest limits, load-bearing on purpose.
12 Could your operation answer these? 24 questions to run against your operation.

Who this is for

Written for you if

  • Your agents already do real work: writing code, running jobs, touching production systems
  • The operation around them grew by accident, and you know it, and nights before releases feel that way
  • You could not say, mechanism by mechanism, what stops a bad agent change tonight
  • You want the discipline without a platform team to build it for you

Skip it if

  • You’re deciding whether to try AI at all
  • Your agents only draft text a human always reviews
  • You want prompt-engineering tips
  • You need a basic CI/CD tutorial
If the honest answer is a person’s name instead of a mechanism, you have an AI operations problem.
Get the field guideBook an Agentic Workflow Product Review