Skip to content
← /work

DevOps for reliable AI-assisted delivery.

DevOps took a decade to figure out how to make infrastructure reliable, and SRE codified it. AI agents are a new worker class with nondeterministic output. Making them reliable means compiled context, validated output, and reviewed knowledge that remains traceable to evidence.

12-Factor AgentOps adapts those hard-won patterns for AI delivery work. For measuring human-AI collaboration sessions, see vibe-check.

> Compile the context, validate the output, keep the evidence and lesson reviewable.

12
factors
4
phases
daily
use since late 2025

// see it run

The ao CLI, recorded live: the toolkit built on these factors.

// the 12 factors

Twelve vendor-neutral principles across a four-phase operational lifecycle: Prepare → Bound → Select → Govern, with Govern feeding back into Prepare.

PREPARE
set up the environment
I. Context Is Everything
II. Track Everything in Git
III. One Agent, One Job
BOUND
constrain what may act
IV. Enforce Least Privilege
V. Research Before You Build
VI. Isolate Workers
SELECT
decide what survives
VII. Validate Externally
VIII. Lock Progress Forward
IX. Extract Learnings
GOVERN
steer and feed back
X. Maintain Reviewed Knowledge
XI. Supervise Hierarchically
XII. Measure Outcomes

// key insight

A few DevOps controls transfer cleanly when the mechanism stays explicit.

DevOps controlAI-delivery mechanism
Versioned configurationVersioned instructions, skills, and acceptance criteria
Least privilegeExplicit tool permissions and write scope
Health checksDeterministic checks plus a fresh verdict
Deployment historyBead, exact candidate, evidence, and verdict

// the engine

KNOWLEDGE FLYWHEEL

Beads record work and evidence. An LLM wiki preserves reviewed knowledge. Future work links what is relevant; stale pages open repair work.

FRESH VERDICT

One bounded candidate is judged outside its author context against unchanged acceptance, changed files, and evidence for each acceptance check.

The deeper thesis: context orchestration over agent orchestration →

// read the methodology

The full methodology: all 12 factors with examples, failure patterns, and implementation guides.

12factoragentops.com →GitHub →