5ccf5fcd90
- canon/standards/work-record-types_v0.1.md (+ machine registry .yaml): work-record umbrella, closed kind registry (workplan/task/intake/ decision/engagement/register-entry), UUIDv7-internal + canonical-name layering, abstract lifecycles incl. intake, promotion as first-class transition, source-anywhere + generated index, tags, budgets, reconciliation loop. status: draft pending ratification - canon/standards/autonomy-lanes_v0.1.md: binky AutonomyPolicy lane model promoted to fleet canon; lane as mandatory spine field; hub-owned time-boxing; attention as WIP-limited workstation. status: draft - workplans/CUST-WP-0060 (hub 4555741c, T01-T07): ratification, terminology v0.2 extension, per-kind schemas, Forgejo CI validation, fix-consistency sidetrack detector (C-25), binky-control pilot with grandfathered ids, stage-3 handoff. Ratification pending as hub decision f4640f9e Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
98 lines
4 KiB
Markdown
98 lines
4 KiB
Markdown
---
|
|
id: canon-autonomy-lanes
|
|
type: standard
|
|
title: "Autonomy Lanes (Fleet) v0.1"
|
|
domain: custodian
|
|
status: draft
|
|
version: "0.1"
|
|
created: "2026-07-20"
|
|
updated: "2026-07-20"
|
|
scope: fleet
|
|
related_workplans:
|
|
- CUST-WP-0060
|
|
supersedes: none
|
|
origin: binky-control/AutonomyPolicy.md (ratified for Binky 2026-07-16, DEC-2026-001)
|
|
---
|
|
|
|
# Autonomy Lanes (Fleet) v0.1
|
|
|
|
> Draft pending founder ratification (CUST-WP-0060-T01). Promotes the
|
|
> binky-control AutonomyPolicy lane model to fleet canon, unchanged in
|
|
> substance. binky-control's `AutonomyPolicy.md` remains the company-level
|
|
> policy instance; this standard makes the lane vocabulary and enforcement
|
|
> rules fleet-wide.
|
|
|
|
## The rule
|
|
|
|
> If the responsible human is unavailable, the system must either continue
|
|
> safely, prepare the next decision, or explicitly defer with evidence. It
|
|
> must not silently idle.
|
|
|
|
Valid states: `proceeding` | `prepared for review` | `deferred by policy`.
|
|
Invalid state: `waiting because unsure`. Uncertainty triggers research,
|
|
comparison, preparation, or risk classification — not paralysis.
|
|
"Ask the human" is never the default.
|
|
|
|
## Lanes
|
|
|
|
| Lane | Name | Agent may | Human involvement |
|
|
| --- | --- | --- | --- |
|
|
| **green** | Safe autonomous | research, summarize, classify, draft, organize, test, prepare | none (human-on-the-loop via logs) |
|
|
| **blue** | Reversible execution | internal docs, backlog updates, local scripts, reports, local commits | none, but logged |
|
|
| **yellow** | Deferred approval | prepare external emails, invoices, offers, releases, payments | async approval via decision records |
|
|
| **orange** | Time-window approval | customer/legal/accounting/banking actions needing business hours | engagement records, batched into command days |
|
|
| **red** | Human-only | signing, strategic commitments, bank/credential changes, sensitive legal/HR/security | always; agents prepare packages only |
|
|
|
|
Optimization target: **maximize green+blue throughput, queue yellow, batch
|
|
orange, protect red from automation.** Risk-tiered gating (in-the-loop for
|
|
irreversible actions, on-the-loop for recoverable ones) is the only
|
|
oversight pattern that scales.
|
|
|
|
## Lane as a spine field
|
|
|
|
`lane` is a **mandatory field on every work record** (see
|
|
`work-record-types_v0.1.md`) and on every agent instance manifest. The
|
|
chain is closed end-to-end:
|
|
|
|
```
|
|
work record.lane → view routing (autopilot / decision / engagement)
|
|
→ harness tool profile (enforced allow-list)
|
|
→ ops-warden credential lane (catalog access)
|
|
```
|
|
|
|
Declaring a lane an item does not hold is a policy violation the harness
|
|
must catch (tool profile refuses the run).
|
|
|
|
## Approval packages (yellow and above)
|
|
|
|
An agent hitting a lane boundary prepares a complete decision package,
|
|
never a bare question: recommended action, reason, evidence links, risk
|
|
level, reversibility, deadline (`needed_by`), attention cost, fallback if
|
|
no response, options.
|
|
|
|
## Human attention is a WIP-limited workstation
|
|
|
|
The responsible human's capacity is modeled like any lane capacity:
|
|
attention budget (minutes/day, max decisions/day, max deep topics/day) and
|
|
availability as first-class state (`available | evening_window |
|
|
unavailable | office_hour_day`), with an explicit escalation allow-list
|
|
when unavailable (critical security incident, payment failure, legal
|
|
deadline). Yellow routes to the decision view, orange to the engagement
|
|
view, both subject to that capacity.
|
|
|
|
**Time-boxing is hub-owned:** `needed_by` / `fallback_if_no_response`
|
|
windows are watched by the hub → NATS → activity-core; a lapsed window
|
|
raises the escalation or executes the declared fallback — never a human
|
|
re-reading a file.
|
|
|
|
## Raising autonomy
|
|
|
|
Autonomy per area is raised only after the system proves reliable there,
|
|
by explicit human decision recorded as a decision work record. Lane
|
|
assignments are auditable history; lowering a lane needs no approval.
|
|
|
|
## References
|
|
|
|
- `binky-control/AutonomyPolicy.md` (origin instance)
|
|
- `canon/standards/work-record-types_v0.1.md`
|
|
- `research/2026-07-19-work-orchestration-best-practices.md` §2
|