Inventory Optimiser Agent · Use case
How can a manufacturer use an AI agent to propose stock levels on its own infrastructure?
An inventory optimiser agent reads consumption history, lead times and seasonality, estimates the safety stock each item needs and proposes a stock level, with the working shown. Planners decide what is set. The agent runs on the manufacturer's own infrastructure.
Too much of one part.
Too little of another.
- ✗ 01Safety stock is set once and seldom revisited, so cash sits in slow items while fast ones run out.
- ✗ 02Consumption and supplier data are commercially sensitive.
Where it stops for a person
Always, before a stock level is changed.Always. Planners set stock levels.
It proposes stock levels.
Planners set them.
Step · 01
Consumption, lead-time and stock data are connected.
Step · 02
The agent reads the history for each item.
Step · 03
It estimates the safety stock from demand, seasonality and lead time.
Step · 04
It proposes a level and shows its working.
Step · 05
Planners review the proposals and set the levels.
What you set up
- Connect the consumption, lead-time and stock data.
- State the service level you want for each class of item.
- Test against a past year.
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 change settings in SAP?
No. It reads from SAP and proposes. Planners make the change.
Can we see how it reached a level?
Yes. Each proposal shows the history it read and its working.
Where is stock data processed?
On your own infrastructure, with a model you serve. Nothing is sent to a public AI service.