Scorecard

This page answers the hardest evidence question on the site: did Verdify make useful greenhouse decisions, or did it merely create plans?

The scorecard is not a single number. It is the relationship between:

  • what the forecast said would happen
  • what the planner decided to do
  • what the greenhouse actually experienced
  • how much stress, water, and cost remained afterward
  • what lessons were extracted for the next cycle

For the exact parameters the planner can change, see AI Tunables Traceability.

Open the live Scorecard dashboardGrafana read-only view

Use this for the continuously refreshed panels. The static snapshot below is the crawler-friendly proof layer.

Current scorecard

Static public API snapshot: 2026-11-17 20:09 MST. Source: evidence snapshot JSON and scorecard API. These values are crawler-friendly receipts; use the live dashboard link above for continuously refreshed panels.

81.7

Today's planner score (served-band compliance)

81.7%

Both-axis time in the served house band

97.4%

Temperature time in the served band

84.3%

VPD time in the served band

3.58h

Hours above/below the served band (both axes)

Nov 16

Last validated plan

Physical crop-band complianceUnavailable

No qualified fixed-panel crop result for this day. Legacy house averages, controller credit and the Sep 4 counterfactual cannot fill this value.

Native route measurementsUnavailable

No scoped native callback diagnostic for this scorecard day. Missing observations are unavailable.

Measurement basisContract 3

House-average readings graded in 5-minute buckets against the band the controller served (band_house_* audit rows). This is not fixed-panel crop compliance and no center probe is measured.

Last validated planiris-20261116-0648

Validated 2026-11-16 16:51 MST with outcome score 5.

Latest plan statusiris-20261116-1648 · awaiting outcome

Written 2026-11-16 16:52 MST; age 27.3h at snapshot time.

Stress breakdownheat 0.00h · cold 0.50h · VPD-high 0.00h · VPD-low 3.08h

Total stress-axis hours can exceed wall-clock hours because temperature and VPD are independent stress axes.

Latest lesson#99 · humidity · high confidence · validated 10x

Mist/fog suppression alone can preserve dew-point safety but leave VPD below band for most of the day. When dp margin is safe, pair mist suppression with a more active dehumidification/ventilation posture and stable dwell timing rather than simply raising mist thresholds all day.

Did the plan improve the outcome?

What to inspect: score trend, both-axis compliance, and stress-axis hours over the last 30 days.

The compliance panel is percent only: temperature compliance, VPD compliance, and total compliance when both axes are inside the firmware-enforced band.

The stress panel is time only: temperature stress hours, VPD stress hours, and total stress hours. Total stress can exceed 24 hours because temperature and VPD are independent stress axes.

Forecast, band, actual

What to inspect: forecast pressure, the actual-to-forecast firmware compliance band, and the actual greenhouse response across the current planning window.

These panels are the direct decision story. The forecast is the external pressure. The stitched green firmware band shows what the ESP32 considered compliant historically and what the dispatcher projects next. Crop target provenance, cfg readbacks, trigger thresholds, and padding math live in the traceability tables rather than as extra trend lines.

The planned posture maps back to bounded parameters in AI Tunables Traceability.

Compliance and accuracy

What to inspect: waypoint compliance and forecast/plan accuracy grouped by day.

Compliance is waypoint-level: planned setpoints compared against actual hourly extremes. Accuracy groups those checks by day so the pattern is easier to inspect.

Tradeoffs

What to inspect: whether water and cost increases correspond to meaningful stress reduction.

The goal is not to minimize cost or water in isolation. The goal is to spend them when they buy meaningful stress reduction.

Journal and lessons

What to inspect: plan outcomes, extracted lessons, and whether repeated lessons have become useful operating constraints.

Open full dashboard ↗