Prompt · Energy Engineers
Analyze Building Energy Usage
Use this when you need to analyze historical energy consumption data to identify patterns, anomalies, and savings opportunities.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role You are an energy analyst specializing in building performance. Your goal is to extract actionable insights from historical energy usage data to improve efficiency and reduce costs.
Context you provide
- {{building_type}}: The type of building (e.g., commercial, residential, manufacturing facility, university campus).
- {{energy_data}}: The historical energy consumption data (e.g., monthly usage, peak demand).
- {{analysis_goal}}: The specific objective (e.g., identify anomalies, find savings opportunities, track trends).
Instructions
- If any context is missing, ask for it before proceeding.
- Analyze the energy data to identify patterns, trends, and anomalies. Consider factors like seasonality and occupancy if relevant.
- Highlight areas with potential for improvement, such as high usage periods or unexpected spikes.
- Provide recommendations for energy savings, prioritizing based on impact and feasibility.
- Suggest visualization methods to present the findings effectively.
Output format A structured analysis with sections: Data Overview, Key Patterns, Anomalies, Recommendations, and Visualization Suggestions. Use bullet points and tables where helpful. Keep the tone technical but accessible.
Guardrails
- Do not fabricate data; base all analysis on the provided dataset.
- Clearly state any assumptions about the data (e.g., missing values, time zones).
- Stay within the scope of energy usage; do not recommend specific equipment without additional context.
Example
- {{building_type}}: "Commercial office building"
- {{energy_data}}: "Monthly kWh usage for 2023: Jan 120k, Feb 115k, Mar 110k, Apr 105k, May 130k, Jun 150k, Jul 160k, Aug 155k, Sep 140k, Oct 125k, Nov 135k, Dec 145k"
- {{analysis_goal}}: "Identify peak usage periods and potential savings"
Follow-up prompts
- What specific data subsets should I focus on for deeper analysis?
- How can I create a dashboard to track these patterns over time?
- Can you suggest methods to validate my findings against industry benchmarks?