PlaysbyMoat8
Back to the library
The workflow guideOperations

Prototype an energy-use recommendation service

Use consumption patterns to identify energy-management opportunities for building operators.

6 implementation stepsAdvanced

How this works

Use consumption patterns to identify energy-management opportunities for building operators.

Prototype an operator review of energy patterns rather than an autonomous building-control system. Relate consumption to occupancy, weather and operating schedules where available, and distinguish a data anomaly from a real efficiency opportunity.

Before you start

Defined operating scope

Building operators have meter history and operating constraints for a limited energy-use review.

Required source material

Obtain Usage history; Operating constraints. If connectors are unavailable, use authorized files with the same fields.

Decision and exception rules

A cumulative meter resets. Correct interval calculation from verified reset information or mark the interval invalid.

Prepare the inputs

meter_series
Required

Timestamped readings and units

Identify cumulative versus interval measurements.

building_schedule
Required

Occupancy and operating hours

Record exceptional events and closures.

operating_limits
Required

Comfort, safety and equipment constraints

Use owner-approved limits.

context_series
Required

Weather or other relevant drivers

Mark missing context and alignment limits.

Implementation, step by step

  1. Establish the working record

    • Confirm the selected records, effective versions and responsible owner.
    • Check meter_series, building_schedule, operating_limits, context_series before beginning. Record the source version and the selected scope; an unavailable value stays unknown rather than becoming an inferred fact.

    Checkpoint: The input record identifies the selected meter_series and any missing required fields.

  2. Validate the meter data

    • Validate timestamps, units, gaps and meter resets before calculating interval usage.
    • Check meter units, interval lengths and resets before comparing consumption.

    Checkpoint: A saved intermediate result for: Validate the meter data.

  3. Identify patterns and candidate changes

    • Compare comparable operating periods and identify unusual baseload or schedule patterns with alternative explanations.
    • Compare only periods with sufficiently understood occupancy and operating conditions.

    Checkpoint: A saved intermediate result for: Identify patterns and candidate changes.

  4. Have an operator review recommendations before testing

    • Prepare bounded recommendations for an operator to review, including expected observation, constraints and a reversible trial plan.
    • Check meter units, interval lengths and resets before comparing consumption.

    Checkpoint: A saved intermediate result for: Have an operator review recommendations before testing.

  5. Reconcile the proposed result

    • Check meter units, interval lengths and resets before comparing consumption.
    • Compare only periods with sufficiently understood occupancy and operating conditions.

    Checkpoint: The listed discrepancies have a named reviewer or an explicit unresolved status.

  6. Package the result and unresolved work

    • This is a concept adaptation; protect comfort, safety and operational requirements.
    • This is a concept-stage recommendation service, not verified energy savings.

    Checkpoint: An energy-opportunity review. Unresolved items remain visible in the review record.

Decisions along the way

A cumulative meter resets.

Correct interval calculation from verified reset information or mark the interval invalid.

Occupancy or weather differs materially.

Avoid attributing consumption differences solely to operating changes.

A recommendation could compromise safety or comfort.

Reject autonomous control and request qualified operator assessment.

What you will produce

building-energy-opportunity-review-result.json

JSON

An energy-opportunity review. Label proposed and completed states separately.

Include: building_id · period · validated_usage · pattern · context_gaps · operator_question · trial_proposal · status · evidence_reference · review_note

building-energy-opportunity-review-review.md

Markdown

Keep the evidence and unresolved decisions needed to apply this result, including exceptions involving context_series.

Include: source_reference · question · owner · next_action

Check the result

  • Check meter units, interval lengths and resets before comparing consumption.
  • Compare only periods with sufficiently understood occupancy and operating conditions.
  • Inspect meter_series and building_schedule in both the original and output; confirm that record identity and interpretation survived the transformation.
  • This is a concept adaptation; protect comfort, safety and operational requirements.

When something goes wrong

A cumulative meter resets.

Correct interval calculation from verified reset information or mark the interval invalid. Retain the affected evidence and recovery status.

Occupancy or weather differs materially.

Avoid attributing consumption differences solely to operating changes. Retain the affected evidence and recovery status.

A recommendation could compromise safety or comfort.

Reject autonomous control and request qualified operator assessment. Retain the affected evidence and recovery status.

A worked example

SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT

Request

Prototype an energy-use recommendation service for the following bounded example; prepare the result for review.

Inputs

Synthetic example: Building B-2 shows 8 kWh each hour overnight for five nights, but one meter gap is followed by a large cumulative reading. Occupancy is unknown on one night.

Expected result

Synthetic expected result: Flag the consistent overnight baseload for review, exclude the invalid interval and request occupancy context. Suggest inspecting scheduled equipment, not automatically turning it off.

Run a small pilot

Start small

Trial a representative batch containing the ordinary case and the exception demonstrated above.

Record the baseline

Record current preparation time, review effort and correction types for the same records.

Agree success criteria

Agree acceptable review and error limits; measure operator-validated opportunities; weather-adjusted consumption and comfort exceptions in a bounded test.

Stop or revise

A recommendation could compromise safety or comfort. Pause affected records and apply this recovery: Reject autonomous control and request qualified operator assessment.

Keep the scope clear

  • This is a concept-stage recommendation service, not verified energy savings.
  • Qualified operators control equipment and protect comfort, safety and service requirements.

Check before using

This is a concept adaptation; protect comfort, safety and operational requirements.

Business activities

  • Review business performance
  • Inspect and maintain physical assets

Editorially adapted workflow; not independently tested.

FROM A RECIPE TO YOUR WORKFLOW

Bring the company context together.

This workflow needs reliable inputs before it needs a better prompt. Moat8 Vault brings working information into a readable archive for the AI tools you use.

For this recipe: Usage history · Operating constraints

Start with one recurring task, agree which sources to use, and review the first result with your team.

Discuss this workflow

What does your team do?

Choose the recurring work you would like to improve.

A field guide, made for work.

Plays is a curated library of anonymized business workflows. Each recipe explains the inputs, steps, tools, and checks you can adapt to your team. These are editorial guides, not independently tested implementations.

When you share a company website, the guide may read a limited number of public pages on that website. Messages and retrieved page text are sent to our AI provider, NVIDIA, to recommend relevant workflows. Share a general description rather than confidential information.

Saved workflows and selected activities stay in this browser. Your chat history and selected company website are kept in this tab and cleared when you reload or start a new chat. The server does not store conversations. Live source monitoring is not enabled.

If you allow analytics, PostHog receives page views and actions such as workflow saves, skill downloads and link clicks. Random browser and session identifiers connect these actions without identifying you by name. Your choice and browser identifier expire after 90 days; sessions restart after 30 minutes of inactivity or 24 hours. We use local storage, not analytics cookies. Messages, company URLs, search text, full referrers and IP addresses are not sent. There are no person profiles or session recordings. You can decline or withdraw in Analytics settings; Do Not Track and Global Privacy Control keep analytics off.

Read the Plays Privacy Notice ↗