Demand Forecasting Agent · Use case
How can a utility use an AI agent to forecast energy demand on its own infrastructure?
A demand forecasting agent forecasts energy demand by hour, day and season from your demand history, weather forecasts and economic indicators, and shows the data and assumptions behind each forecast. Analysts check the forecast before it is used for planning or trading. The agent runs on the utility's own infrastructure.
Forecasts built in spreadsheets.
On assumptions nobody can see.
- ✗ 01Forecasts are rebuilt by hand in spreadsheets, and the assumptions behind them are hard to see.
- ✗ 02Demand data by area is commercially sensitive.
Where it stops for a person
Before a forecast is used.A forecast is an estimate. An analyst checks it before it is used for planning or trading, and the agent places no trade.
It forecasts and shows its working.
Analysts check it.
Step · 01
Demand history is connected with read-only access.
Step · 02
The agent reads the weather forecast and the indicators you choose.
Step · 03
It forecasts demand for the period asked.
Step · 04
It shows the data and assumptions it used.
Step · 05
An analyst checks the forecast before it is used.
What you set up
- Connect the demand history.
- Choose the indicators it may use.
- Test against past periods where you know what demand was.
Where it runs
The agent, its knowledge store and the model run on infrastructure you own or control. You choose the model and serve it yourself, so questions, documents and answers are not sent to a public AI service.
How you get it today
This page is labelled Use case: the agent is built in Katonic Studio. You describe the job, connect what is named above, add test questions and release the agent once it passes them. When the Catalog holds a tested template for this job, this page will carry the Template label and show how to take it.
Does the agent place trades?
No. It forecasts. People decide what to do with the forecast.
How do we know how accurate it is?
You score it against past periods before release and after each change.
Where is demand data processed?
On your own infrastructure, with a model you serve. Nothing is sent to a public AI service.