The Autonomy Bill
Updated
AdvancedWhat you'll learn
~15 min- List the incremental cost lines a guarded agent adds, and name the two adjacent bills this one is not
- Explain which approval-load inputs the current receipt log does and does not record, and leave approver hours reader-supplied
- Explain why the storm night's one-minute call spacing is not a staffing model
What it is: the incremental cost of guarding one agent — the gateway and policy work, the approver hours an ask-class action actually spends, the verifiers and compensators an engineer writes once and maintains after, the halt drill, and the receipt storage this training’s five modules already built.
What it buys: a bill leadership can fund or push back on, priced from the same agent’s own receipt log rather than from a vendor demo or a guessed weekly allowance.
What to fund: the approver hours the log actually shows for classes routed to ask, the drill cadence 4.3 set, and the storage and anchoring a receipt chain needs to outlive the agent that wrote it — never a total borrowed from a different training’s bill.
Before the detail — Artifact: the autonomy bill, costed from the agent’s own log. Status of what follows: reusable guidance — no standard prices a guarded agent for you.
Prompt first: draft the bill, leave every hour blank
Open your workspace agent, switch to Plan mode on your action register and weekly receipt stats, and start with (if you do not have live exports or files handy, ask it to generate a small Meridian practice sample from the lesson’s scenario first):
Using our agent's action register and weekly receipt stats, draft a five-line autonomy bill template with bracketed inputs for engineering, approver time, verifiers and compensators, halt drills, and receipt storage. Mark unlogged counts NOT YET LOGGED.Check that the plan or draft covers:
- Five required bill categories with bracketed inputs:
- Gateway and policy engineering:
[H_build]hours to stand up the guard, envelope, and bypass tests, plus[H_maint]hours per month. - Approver hours: for each action class actually routed to
askon the register,[N_per_week]approvals times[H_per_approval]hours times[approver rate]. - Verifiers and compensators:
[H_verify]hours per mutating tool’s independent post-condition check, plus[H_compensate]hours per declared inverse. - Halt drills:
[H_drill]hours per drill times[drills_per_year]at Lesson 4.3’s cadence. - Receipt storage and anchoring:
[cost_storage]for the retention window and[cost_anchor]for the anchoring cadence.
- Gateway and policy engineering:
- No invented numbers: every unmeasured count marked
NOT YET LOGGEDrather than filled with an external average.
If the first pass fills in an estimated hour count or approval rate, follow up with: "Replace any estimated hours or weekly approval counts not in our receipt stats with bracketed placeholders or NOT YET LOGGED."
An agent can total a spreadsheet from any numbers it is handed; only the receipt log and the person who staffs approvals know which bracket is a real weekly count and which is a guess dressed as one. Writing NOT YET LOGGED keeps an unsupported estimate from becoming contract risk.
What this bill prices, and what it does not
This bill prices the incremental cost of guarding one agent — the machinery this training’s first five modules built, priced out line by line: the envelope, the approvals, the verifiers and compensators, the kill switch’s drill, and the receipt chain. It is not a headcount request for running MU-AI-011 unguarded, because there is no such option this training offers — running it unguarded is the release AI Assurance 4.3 (a separate training in this series) has not approved.
Two adjacent bills price different things, and this one fences against both in one line each. AI Assurance 6.3’s bill: reviewer hours, ten systems — that sheet prices the reviewer bench that reads release-decision records across a whole portfolio, not the gateway in front of one agent. Operating in Production 6.2’s bill: on-call seats, one page — that sheet prices the rotation that answers an incident once it exists, not the machinery built to keep an agent from causing one. A leader who folds any of the three into the others is funding one line twice and leaving another at zero.
Approver hours: the log already answers this
The register (1.3) routes each action class to a decision — allow, ask, or a standing deny — and only the ask classes cost an approver’s time. In MU-AI-011’s own envelope, draft_work_order and update_work_order_priority are allow: no approver reads them. pre_position_crew (compensable) and send_dispatch_notice (irreversible, two people) are ask: every attempt costs an approver some time, not zero. Pricing “approver hours” against the whole register instead of the ask rows alone is the single most common way this bill overstates itself.
receipts_query.py --stats counts receipt rows, not approval events or elapsed review time. In this run, ask=1 counts only the action that cleared approval; the one-signature refusal is stored as deny, while the 14-crew request never reached approval. Therefore neither --action pre_position_crew --stats nor by decision ask=1 is an approver-hours count. Until the query exposes accepted and rejected approval presentations separately, write NOT YET LOGGED for approval volume; handling duration remains reader-supplied.
Verifiers, compensators, and the drill
Every mutating tool in the envelope needs an independent post-condition check (3.2’s subject) and, where the class allows it, a declared inverse (3.3’s subject) — both are engineering hours a team writes once and then maintains as the target system changes underneath. Neither cost belongs to the agent’s runtime; both belong to this bill, because a verifier or a compensator that nobody funded to maintain is one silent target-system change away from the false-success clamp 3.2 already named.
The halt drill (4.3) is a cost with a cadence, not a one-time build: rehearsing report-only, then enforce, and measuring time-to-halt is staffing time repeated on a schedule the drill’s own owner sets, and it belongs on this bill at that cadence — never priced once and forgotten. Receipt storage and anchoring close the list: retaining a growing, hash-chained log and running whatever anchoring cadence the organization picks both cost something, and neither figure exists in this substrate’s committed files, because storage pricing is an environment fact this training does not carry.
The storm night’s clock is not a cost model
The nine-call run in the next lesson moves through a full night’s worth of decisions one minute apart — a scripted cadence built so a classroom can watch every step, not a claim about how often a real crew-dispatch agent acts or how long an approver actually takes to read a card. Multiplying that spacing into a staffing number invents an hour this training never claimed. The gate’s committed timings prove the guard’s steps execute in the right order and halt on command; they answer nothing about cost, and this bill’s only honest inputs are the brackets the reader supplies from a real log, a real approver, and a real storage bill.
Treating a demonstration’s clock as a cost line is the fastest way to turn a defensible bill into one the first auditor throws out.
Stop and escalate when a bracket in the prompt above cannot be filled honestly — no receipt log old enough to count approvals, no named engineer maintaining a verifier, no answer for storage cost. Only the agent’s named owner (Distribution Operations, Mgr. L. Tran, per 1.1) can decide whether to fund the missing line or hold the agent at its current autonomy level until it is answered.
A budget proposal lists only a gateway-license quote and treats the storm transcript's scripted call spacing as the approver-staffing rate. What is wrong with this bill?
Key takeaway
The autonomy bill prices what guarding MU-AI-011 costs beyond running it at all: gateway and policy engineering, approver hours reader-supplied for the classes that actually route to ask (the log names which classes those are; it does not yet total the hours), verifier and compensator maintenance, the halt drill’s cadence, and receipt storage and anchoring — every line supplied by the reader’s own log, never invented and never folded into an adjacent portfolio-review or on-call bill. The storm night’s own clock proves the guard’s order of operations, not a staffing rate. The next lesson turns from what this guard costs to what it has to show before an action class earns a higher level.
- LEADERSHIP DECISION
- fund the guard's incremental lines from the agent's own receipt log, distinct from the assurance bill and the operations bill
- PRACTITIONER ACTION
- name the classes routed to ask from the register, not the log's action counts; write NOT YET LOGGED for approver hours until then
- SUCCESS MEASURE
- zero bill lines sourced from a demonstration's timing instead of a real log or a named engineer - audit finding avoided