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 energy engineers

Project Financial Model Refresh Agent

A current financial model whose returns and risks are known against hurdle rates at any time.

AnalysisAutomationScience and research
See how it worksGet access
Project Financial Model Refresh Agent: what goes in, what the agent does and what you get

What it does

A solar or wind project model built six months ago still uses the old module price, the old power price curve and the old interest rate. This agent updates those inputs from your chosen sources: equipment quotes, power price forecasts, resource data, interest rates and tax rules. It reruns the returns, compares them to the hurdle rates and shows what moved the result. Where margins are thin, it runs sensitivities on the key assumptions such as price, output and cost, and tests the downside case. It lists every input changed with its source. You approve the update. Edge case: a quote past its validity date is not used and is flagged.

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, continueYes, continueApprovedNoNo 1 STARTS WHEN Monthly run or input change 2 USES A TOOL Pull new prices, quotes, forecasts and rates fromthe sources 3 CHECKS THE RESULT Is each new input dated, sourced and still valid? If not: drop the input and keep the old value with aflag. Back to step 2. 4 DOES Update the model inputs and log each change 5 USES A TOOL Rerun returns: IRR, NPV and payback 6 DOES Compare returns to the hurdle rates and explain whatmoved 7 CHECKS THE RESULT Is the margin over the hurdle rate above the safetymargin? If not: run sensitivities on price, output and cost, anda downside case. Back to step 4. 8 DOES Write the summary with changes, results and risks 9 YOU APPROVE Engineer approves the update 10 RESULT Refreshed model and change log
Read the steps as a list
  1. Monthly run or input change
  2. Pull new prices, quotes, forecasts and rates from the sources
  3. Is each new input dated, sourced and still valid?If not: drop the input and keep the old value with a flag. Back to step 2.
  4. Update the model inputs and log each change
  5. Rerun returns: IRR, NPV and payback
  6. Compare returns to the hurdle rates and explain what moved
  7. Is the margin over the hurdle rate above the safety margin?If not: run sensitivities on price, output and cost, and a downside case. Back to step 4.
  8. Write the summary with changes, results and risks
  9. Engineer approves the updateThe agent waits here for your OK.
  10. Refreshed model and change log

How it decides

It replaces inputs with newer sourced values, then recomputes returns. Thin margins trigger sensitivity cases and a downside test.

  • Return within 1.5 points of the hurdle: run sensitivities
  • Quote older than its validity date: do not use
  • Downside case under the hurdle by over 3 points: flag as a risk
  • Input change moves IRR by over 1 point: highlight in the summary

Make it yours

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

  • Input sources
  • Hurdle rates
  • Safety margin in points (default 1.5)
  • Sensitivity ranges
  • Refresh schedule

What keeps you in control

It always asks you first

  • The updated model for sharing
  • Any change to base assumptions

Hard limits

  • Never overwrite the base case without approval
  • Never use an unsourced input

It stops when

  • Done: model refreshed and approved
  • Stop: key inputs unavailable

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 happensFor a 12 MW solar project, the agent updated module price to 0.27 dollars per watt from 0.31 and the power price forecast down 4 percent. IRR moved from 9.4 to 8.9 percent against an 8.5 hurdle. The margin was inside the 1.5 point band, so the check failed. A sensitivity showed a 10 percent output drop gave 7.6 percent. The engineer approved the update with a risk note.

More agents for energy engineers

Analysis · Science and research

Life Cycle Inventory Data Gap Agent

Close or document every material data gap and show how it affects the result.

11 steps2 checks2 jobs
Analysis · Quality control

Utility Bill and Tariff Audit Agent

Every bill is verified against the tariff and meter data, and tariff savings are quantified.

11 steps2 checks2 jobs
Decisions · Science and research

Efficiency Measure Screening Agent

A ranked, interaction-aware shortlist of measures that meets the client's payback and savings targets.

10 steps2 checks2 jobs
Analysis · Decisions

Demand Charge Peak Shaving Agent

Lower monthly peaks through changes that do not disturb production, verified against the next bills.

10 steps2 checks2 jobs