Goal inbox
Durable · resumes after restart| GOAL | STATUS | STAGE | AGENTS | BUDGET | NEXT ACTION |
|---|---|---|---|---|---|
| Crown weekly ops brief | Waiting approval | Decision | Scout → Analyst → Maker → Auditor | 4/6 calls | Approve decision packet |
| Vendor quote comparison — linens | Running | Evidence | Scout, Index | 1/6 calls | None — auto |
| DJ SAVAG3 October booking sheet | Running | Draft | Maker | 3/6 calls | None — auto |
| WGU capstone outline review | Blocked | Evidence | Scout | 0/6 calls | Add missing source file |
| Client Room rollout checklist | Complete | Receipt | Maker, Auditor | 6/6 calls | Export audit packet |
Goals persist locally · every state change writes an event · restart-safe resume
Workroom
Crown weekly ops brief · Stage 5 of 6 — DecisionDECISION PACKETRecommend staffing plan for week of Sep 14
Confidence 78%
Weekend demand requires +2 servers Sat and +1 Sun vs. current roster. [1][3]
Linen vendor B is 12% cheaper but has a 5-day lead time — schedule risk for Sat events. [2] · conflicting
Overtime cost stays under the $650 weekly cap if Sat crew caps at 9. [4]
Evidence used4 sources · 2 verified hashes
1 conflicting pair flagged
1 conflicting pair flagged
RisksVendor B lead time
Sat weather (outdoor)
Sat weather (outdoor)
AlternativeKeep vendor A; +$78 cost, zero schedule risk
Auditor noteIndependent pass · no objections
1 caveat on [2]
1 caveat on [2]
Autonomy ceiling: AUT-2 · execution requires owner approval
✓ Approved — receipt logged, work dispatched
PIPELINE
1 GoalDONE
2 EvidenceDONE
3 PlanDONE
4 DraftDONE
5 ReviewYOU
6 Action + receiptLOCKED
EVIDENCE COVERAGE
Supported claims4
Weak / conflicting1
Unsupported0
Stale sources0
Agents & fleet
12 seats · 7 active · routes are per-agentSc
Scout
Autonomy AUT-1 · tools: read evidence
Route: free-fast · fallback local
Eval: PASS 9/10 · drift 0.02
An
Analyst
Autonomy AUT-1 · tools: read, structure
Route: mid-tier · fallback free
Eval: PASS 8/10
Mk
Maker
Autonomy AUT-2 · tools: draft, calc
Route: strongest model
Eval: PASS 9/10
Au
Auditor
Autonomy AUT-1 · fresh context · decorrelated route
Route: different provider than Maker
Eval: 1 caveat on [2]
Sw
Switchboard
Autonomy AUT-0 · scope keeper · 0 model calls
Deterministic service
Last: kept run in scope
Or
Oracle (computer)
Autonomy AUT-3* · requires owner dispatch
Shared computer queue · free-only
Hold: owner hold active
Passports bind role, tools, route, budget and data boundary · "connected" only after live probe
Receipts
Append-only · exportable audit trail| TIME | ACTOR | EVENT | DETAIL | HASH |
|---|---|---|---|---|
| 20:41:07 | Maker | draft.checkpoint | Staffing plan v3 · 2,140 out tok | a91f… |
| 20:38:52 | Auditor | review.complete | 1 caveat · verdict: PASS w/ note | 7c02… |
| 20:31:19 | Switchboard | scope.check | Run kept in scope · no expansion | e4d8… |
| 20:29:44 | Index | evidence.hash | 4 sources sealed · 1 conflict flagged | b3aa… |
| 20:12:03 | Owner | goal.create | Crown weekly ops brief · budget 6 calls | f190… |
Receipts never rewritten · restore creates a recovery copy, never overwrites
Gates & policy
Fail-closed · a model opinion cannot approve workEvidence & claims
CLEARMechanical verification + human review. Source hashes run per workflow.
Information boundary
CLEAROutgoing payloads scanned for secret patterns. Heuristic, not comprehensive.
Execution authority
OWNER HOLDHost-enforced call limits. Durable hold survives restart. Model replies cannot expand grants.
Publication
ABSENTNo publish/send tool installed. Export uses owner-selected native Save dialog.
Policy simulator
Before any run: shows what leaves the device, which tools may fire, what needs approval.
Drills
Make-it-fail: provider outage, bad evidence, injection attempt — next drill Fri 02:00.