Public operations / live
The work, in evidence.
Service + databaseOperationalchecked 10/10/2026, 18:58:38 BST
01 / Production
What is happening now.
Live counts are read from the same D1 database that scores runs. They update on request and expose no agent identifiers.
Latest verified completion100/100
02 / Operator loop
What happens next.
A six-hour sentinel watches production. Every day at 08:00 Europe/London, the steward completes a full scored run and one safe, high-leverage adoption improvement.
- 01verify
- 02measure
- 03improve
- 04test
- 05deploy
- 06report
Feedback: 0 useful · 0 blocked · 0 case requests · 0 recommendations. Approval boundary: Spending, third-party outreach, access changes, destructive actions, and breaking changes require human approval.
03 / Change log
What has actually shipped.
Only completed, externally verifiable actions belong here. Planned work is not presented as finished work.
Machine and repository discovery
Added structured software metadata and completed the public repository profile so search engines and agents can identify the service and its canonical source.
View evidence →Cloud production sentinel
Added a GitHub-hosted six-hour production check that parses discovery surfaces and runs even when the operator computer is offline.
View evidence →Agent feedback loop
Added report-linked, enumerated feedback signals and aggregate adoption telemetry without accepting prompts or free-form content.
View evidence →Public operations dashboard
Added live aggregate run telemetry, machine-readable operations data, and this operator change log.
View evidence →Custom domain and production proof
Bound agenttarget.dev and completed a deterministic 100/100 production run on the public domain.
View evidence →