Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for facilities managers

Building Energy Anomaly Agent

Find and fix energy waste quickly

Building Energy Anomaly Agent: what goes in, what the agent does and what you get

What it does

Energy waste often comes from equipment running at night, heating and cooling fighting each other, or a broken sensor, and it hides in a monthly bill. Each day this agent reads meter and building management data and compares use with a baseline adjusted for weather and occupancy. Planned events and holidays are excluded. It flags use more than 15 percent above baseline for three days in a row, broken down by time and system, and checks night use against schedules. It suggests the most likely cause and a check for the technician. The facilities manager approves the technician check and any change to schedules or set points. After the fix, it compares use again. If waste continues, it suggests the next likely cause and loops back. Edge case: a sensor reading that jumps to an impossible value is treated as a sensor fault first.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
ApprovedYes, continueNo 1 STARTS WHEN Daily run 2 USES A TOOL Read meter and building system data 3 DOES Compare with weather and occupancy baseline 4 DOES Flag unusual use and suggest causes 5 YOU APPROVE Facilities manager approves the technician check orschedule change 6 USES A TOOL Compare use after the fix 7 CHECKS THE RESULT Is use back to baseline? If not: suggest the next likely cause. Back to step 4. 8 RESULT Energy anomaly log with savings
Read the steps as a list
  1. Daily run
  2. Read meter and building system data
  3. Compare with weather and occupancy baseline
  4. Flag unusual use and suggest causes
  5. Facilities manager approves the technician check or schedule changeThe agent waits here for your OK.
  6. Compare use after the fix
  7. Is use back to baseline?If not: suggest the next likely cause. Back to step 4.
  8. Energy anomaly log with savings

How it decides

It flags use more than 15 percent above the weather-adjusted baseline for three days in a row.

  • 15 percent over baseline for three days
  • Events and holidays excluded
  • Night use checked against schedules

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Baseline method
  • Threshold (default 15 percent)
  • Excluded dates
  • Buildings in scope

What keeps you in control

It always asks you first

  • Schedule or set point changes
  • Technician call-outs

Hard limits

  • Never changes building system settings itself
  • Never overrides life safety systems

It stops when

  • Done: use back to baseline
  • Stop: needs capital repair

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensIn the week of January 13, night use in building B rose 22 percent above baseline for four nights. The first suggested cause, the lighting schedule, checked out fine, so the recheck failed. The next cause was an air handler running all night after a controls update. The manager approved resetting its schedule. Night use returned to baseline, saving about $600 a month.

More agents for facilities managers