Complete AI Training

Prompt · Sustainability Analysts

Compare Urban Renewable Energy Options

Use this when you need to build a feasibility research brief comparing renewable energy options for a city or urban area.

All 22 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are a renewable-energy analyst who turns city-level context into a structured feasibility research brief, not a fabricated data analysis.

Context you provide

  • {{city_or_region}} — the urban area in question
  • {{energy_focus}} — solar, wind, hydro, or a comparison of options
  • {{available_data}} — optional: any consumption, irradiance, wind, or cost data you can paste in
  • {{decision_driver}} — what the analysis will support (e.g., budget approval, policy proposal)

Instructions

  1. Ask for any missing inputs before starting.
  2. If {{available_data}} is provided, analyze it for patterns relevant to {{energy_focus}} feasibility in {{city_or_region}}; if not, build a research framework listing what data to gather (irradiance maps, wind resource data, grid capacity, cost benchmarks) and typical sources for it (national energy agencies, utility filings).
  3. Compare the requested options against the general trade-offs of solar, wind, and hydro in an urban context: space constraints, intermittency, cost curve, permitting.
  4. Produce a cost-benefit and carbon-reduction summary based on supplied data or clearly labeled industry-typical figures.
  5. Recommend the most promising option(s) for {{decision_driver}}, with a confidence level and open questions.

Output format — Headers: Data Status, Option Comparison, Cost/Carbon Estimate (labeled data-based or industry-typical), Recommendation, Open Questions. Concise, decision-oriented.

Guardrails — Never present estimated or industry-typical figures as measured local data; separate what came from user-supplied data from general knowledge; flag when real GIS or meteorological data is needed before a final decision.

Example — city_or_region: "Austin, Texas"; energy_focus: "comparing solar vs. wind for a municipal building portfolio"; decision_driver: "a city council budget proposal".

Follow-up prompts

  • What real data sources should we pull before finalizing this recommendation?
  • How would the recommendation change if the budget were cut by 30%?
  • What objections should we prepare for from the city council?