Baseline vs AI Planning Agent

This is an operational comparison, not a controlled A/B test, and it does not isolate the AI planning agent as the only variable. The baseline window is the April 22-25, 2026 planner-offline run already documented in the public outage story. The comparison window is April 26-May 2, 2026, when normal AI-assisted planning resumed.

The comparison is still useful because it answers the skeptical reader’s first question: when the planning loop is online, do the public scorecards look different from the period where the ESP32 had to keep running without normal AI plans?

For the exact parameters the AI planning agent can change when it is online, see AI Tunables Traceability.

For the broader caveat language, see the AI Greenhouse FAQ. For the live receipts behind this page, use the Scorecard, Operations, and the planning archive.

Periods Compared

2026-04-22 to 2026-04-25

Planner offline window: 4 days, 0.0 AI planning-agent plans/day.

2026-04-26 to 2026-05-02

Planner online window: 7 days, 3.0 AI planning-agent plans/day.

Summary Table

MetricPlanner offlinePlanner onlineChange
Average AI planning-agent plans/day0.03.0+3.0
Both-axis compliance (served house band)20.6%54.7%+34.1 pts
Temperature compliance44.9%70.9%+26.0 pts
VPD compliance30.3%74.5%+44.2 pts
Hours outside the served band/day (both axes)29.9h13.1h16.8h lower
Metered water/day (all uses, reporting only)429.6 gal240.1 gal189.5 gal lower
Runtime-modeled electric energy/day (informational)19.1 kWh29.1 kWh10.0 kWh higher
Nominal-model cost/day (informational)USD 7.89USD 8.31USD 0.42 higher
Planner score20.654.7+34.1

Confounders To Keep In View

This comparison is useful, but it is not weather-normalized proof that the AI planning agent caused every improvement. The planner-online window was cooler, more humid, and lower-solar on average, which likely made VPD and heat stress easier. The table below makes those confounders explicit instead of burying them in caveats.

FactorPlanner offlinePlanner onlineReading
Outdoor temperature55.9°F avg / 83.6°F max47.8°F avg / 73.5°F maxThe planner-online window was cooler, reducing heat-load pressure.
Outdoor VPD / humidity1.19 kPa avg0.55 kPa avgThe planner-online window had less dry-air pressure, so VPD compliance was easier to recover.
Solar irradiance262 W/m² avg205 W/m² avgLower solar load reduces overheating and evaporative demand.
Manual interventions0 logged crop events0 logged crop eventsLogged event counts are shown explicitly, but operator activity is not controlled like a lab experiment.
Hardware changesNo major hardware change is asserted hereNo major hardware change is asserted hereThe comparison uses the same greenhouse and controller boundary, but it is not a locked hardware trial.
Crop mix / active bandsSame public crop-control modelSame public crop-control model, plants still agingCrop targets are comparable enough for an operational receipt, not for yield attribution or agronomic proof.

How To Read The Receipt

This page uses generated tables instead of re-embedding the Scorecard dashboard. The comparison window is fixed, the metrics are pulled from the same tables behind the public scorecard, and the caveats stay on the page with the numbers.

For the live rolling charts, use the Scorecard.

Resource Tradeoffs

The comparison is more useful when stress is shown beside what the greenhouse spent trying to reduce it. Cost, water, and misting are not success metrics and are not part of the planner score. They are shown so the resource bill stays visible beside the climate outcome.

Daily Rows

DatePlansBoth-axisScoreStressVPD-highHeatCost
2026-04-22030.9%30.926.2h12.8h9.4hUSD 6.14
2026-04-23019.2%19.227.8h15.6h2.0hUSD 9.16
2026-04-2403.0%3.040.8h22.5h7.1hUSD 8.43
2026-04-25029.2%29.224.7h12.7h8.7hUSD 7.82
2026-04-26439.7%39.716.3h2.7h4.3hUSD 8.97
2026-04-27224.7%24.723.6h4.6h1.9hUSD 5.58
2026-04-28353.4%53.414.3h4.5h3.2hUSD 6.21
2026-04-29373.7%73.76.9h3.3h0.7hUSD 8.44
2026-04-30269.2%69.27.4h4.8h0.0hUSD 10.97
2026-05-01265.6%65.69.5h5.3h1.4hUSD 7.86
2026-05-02556.6%56.613.7h7.2h3.3hUSD 10.13

Definitions

Both-axis compliance (served house band)daily_summary.compliance_pct

Share of 5-minute buckets in which the house-average temperature and VPD were both inside the band the controller served (the band_house_* audit rows), graded by the database. It is a house-level pass/fail against the served band, not a per-zone or per-plant outcome.

Hours outside the served band/dayAbove + below, temperature + VPD

Summed daily hours above or below the served band from the database's band grade. This is not capped at one axis; a hot-dry hour can count on both.

Planner scoredaily_summary.compliance_pct

The planner score is served-band compliance at full weight. Water, energy and cost are informational and never part of the score. It is useful as an operational KPI, not as a yield claim.

Metered water/daydaily_summary.water_used_gal

Quality-filtered meter total for every use, including house and hose water. Planning water (climate wetting plus wall irrigation and fertigation) is a separate figure.

Runtime-modeled electric energy/daydaily_summary.kwh_estimated

Electric energy from published equipment wattage multiplied by observed on-time; metered kWh is retained separately as diagnostic evidence.

Cost/dayElectric + gas + water

A nominal-model estimate from runtime and published rates, reported for context only. Electric heat is the primary heat source by design; its runtime is not something the planner minimises.

Caveats

  • Weather, crop load, hardware state, and operator activity were not identical across the two windows.
  • The baseline is a real outage window, not a hand-picked fixed-rule controller experiment.
  • The strongest claim is not that the AI planning agent guarantees better outcomes every day. The useful claim is that the system makes planner availability, physical stress, cost, and score visible enough to audit.
  • This is not a yield, profit, or controlled-trial claim. It is a public operational receipt; see the AI Greenhouse FAQ for the claim boundary.
  • Known physical and instrumentation limits still apply, including weather, sensor coverage, water attribution, and firmware-change risk. See Climate Control, Resource Use, and Safety Architecture.

Reproducibility

This page is generated by scripts/generate-baseline-vs-iris-page.py from daily_summary, plan_journal, climate, and crop_events.

For raw public-safe data, use the 7-day climate CSV, 30-day plan outcomes CSV, and dataset notes. The current public snapshot is available from the evidence snapshot API.

Where To Go Next