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 sustainability managers

Sustainability Target Tracking Agent

Show every site its progress against targets while there is still time to act.

Sustainability Target Tracking Agent: what goes in, what the agent does and what you get

What it does

Energy, waste and fuel data sit in utility bills and site reports, and the annual report is the first time anyone sees if a site is off track. This agent collects utility, waste and fuel data from each site every month and converts it to the reporting units. It compares each site against its target path and checks for missing or implausible readings, such as a meter reading that is ten times last month's. It asks the site for corrected data, then drafts a variance note with suggested actions. The VP approves and sends it to site leads. Edge case: a site with a new building opening mid-year gets its target path adjusted before comparison.

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
Yes, continueApprovedYes, continueNoNo 1 STARTS WHEN Monthly data cycle begins 2 USES A TOOL Collect utility, waste and fuel data from each site 3 DOES Convert to the reporting units 4 CHECKS THE RESULT Is each reading complete and plausible against lastmonth and last year? If not: Request corrected data from the site and waitfor the reply. Back to step 2. 5 DOES Compare each site with its target path 6 DOES Draft a variance note and suggested actions for eachsite behind target 7 YOU APPROVE VP approves the notes before they go to site leads 8 USES A TOOL Send the notes and record the replies 9 CHECKS THE RESULT Did flagged sites improve in the next month? If not: Escalate the site with a stronger actionrequest. Back to step 5. 10 RESULT Monthly sustainability dashboard
Read the steps as a list
  1. Monthly data cycle begins
  2. Collect utility, waste and fuel data from each site
  3. Convert to the reporting units
  4. Is each reading complete and plausible against last month and last year?If not: Request corrected data from the site and wait for the reply. Back to step 2.
  5. Compare each site with its target path
  6. Draft a variance note and suggested actions for each site behind target
  7. VP approves the notes before they go to site leadsThe agent waits here for your OK.
  8. Send the notes and record the replies
  9. Did flagged sites improve in the next month?If not: Escalate the site with a stronger action request. Back to step 5.
  10. Monthly sustainability dashboard

How it decides

Compares each site's year-to-date result with its target path and flags a site more than 5% behind; implausible readings are held back and requested again.

  • Reading more than 3 times last month is held for checking
  • Site more than 5% behind path is flagged
  • Missing data for 2 months escalates to the VP
  • Targets change only with VP approval

Make it yours

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

  • Variance threshold (default 5%)
  • Plausibility limits
  • Metrics and sites
  • Data deadline
  • Who receives notes

What keeps you in control

It always asks you first

  • Notes to site leads
  • Any change to a target
  • Any figure used in external reports

Hard limits

  • Never publish figures externally
  • Never change a target

It stops when

  • Done: dashboard issued
  • Stop: data not available
  • Stop: targets under review

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 happensThe agent receives gas data for a plant showing 48,000 kWh against 12,000 the month before. The plausibility check fails. It asks the site, which replies that the meter was misread and corrects it to 14,500. The variance is then 9% behind path. The VP approves a note suggesting a heating schedule review.

More agents for sustainability managers