Live Greenhouse Data and Scorecards
Verdify should be judged by what the greenhouse actually did. This page is the evidence map: where to go for live operations, planning quality, costs, the Baseline vs AI Planning Agent comparison, generated archives, APIs, and public-safe exports.
The linked pages carry the Grafana panels, generated tables, and dated snapshots. This page should stay a map, not a second dashboard.
Evidence Summary
The shortest public receipt, with caveats kept next to the comparison.
Use this to inspect whether plans moved the greenhouse toward target bands instead of only producing prose.
Use this to answer what the greenhouse is doing now and whether intervention is needed.
Use this to see what utility work happened, when it happened against solar and weather pressure, and what the public rate model says it cost.
Canonical Homes
The comparison page owns the launch-window contrast; the Scorecard owns ongoing scorecards and forecast-vs-actual proof.
Operations owns live status, alerts, controller state, and equipment-now proof; Equipment owns inventory and relay-backed device context.
The archive owns daily plan records and outcomes; AI Tunables owns the exact writable parameter contract.
Resource Use owns utility timing, public rates, daily cost, seasonal cost shape, and solar-alignment proof.
Archives
- Daily plans are the generated lab notebook: conditions, decisions, experiments, and outcomes.
- Baseline vs AI Planning Agent compares the planner-offline window to the following online window.
- Generated lessons are the validated operational findings the planner reads before future plans.
- 30-day hourly performance CSV, 7-day climate CSV, 30-day plan outcomes CSV, and dataset notes provide public-safe samples: enough to inspect claims, not a raw dump of every private operational feed.
If a claim does not have a clear home in that list, it probably is not ready to be a public claim.