Four curated sequences

Start with the narrative. This is how the rollout actually sequences through the first quarter — week one, the AGENTS.md pass, the gates, and the conversation you earn the right to have at week ten.

Once you know how the sequence goes, this is the artifact the team converges on. Ten lines, plain English, the specific failure modes each line prevents.

The patterns inside the repo that make the practice durable: instruction hierarchy, hooks, shared memory, and workflows as version-controlled processes.

The loop itself — draft, verify, revise — applied specifically to agents, with the verification strategies that separate generators from agents.

The ongoing risk most rollouts miss: borrowed competence eroding judgment. What to do about it, at the team and the individual level.

The overview of the audit itself — the four tracks, what each one delivers, and why you do them in parallel rather than in series.

The cost track in depth. What to measure, what the cloud console lies about, and how to derive a per-unit-of-work cost that survives scrutiny.

The reliability track. A taxonomy of what breaks on GPUs in production — from thermal throttling to VRAM fragmentation — and how to catch each early.

The SLO track. How to define meaningful latency, error, and saturation targets for inference, and what to do when the error budget is spent.

How the roadmap lands in operations. GitOps patterns that make on-prem or hybrid GPU as boring to run as managed cloud services.

Start with the national context. What changed between Meaningful Use and TEFCA, and what still blocks plug-and-play apps despite a decade of standards work.

The operational playbook: contracts as assets, observability first-class, executable docs, and support workflows that compound.

A specific failure mode — an "enhanced best match" trap where filter and mode parameters collide — and the defensive pattern that fixes it on both sides.

The reference implementation. How Source Profiles, a three-phase parsing pipeline, and a workflow DSL turn messy legacy formats into semantic events without a one-off codebase per feed.

Start with the shape of a reliable agent: an explicit loop, bounded tools, verification against concrete criteria, and visible operator state.

The repo as control system. Hooks, memory, tasks, and workflows that give agents durable context and enforce the invariants you care about.

The judgment-erosion risk. How to keep agents from becoming a substitute for engineering thinking instead of a force multiplier.

The policy that makes the practice auditable. Ten lines the team converges on, with a quarterly review rhythm.