Agent Marketplace · Forecast to Deliver
Demand Forecaster Agent
Projects short-term demand from sales history and seasonality.
How to use this agent
Stage 1 of 5
See what it needsRead the input data the agent asks for and where each figure usually comes from.
Stage 2 of 5
Run the demoPress the demo button to see a full run on a fictional company. Nothing is saved.
Stage 3 of 5
Get the templateThe tool opens once it is approved; the template downloads from there.
Stage 4 of 5
Add your dataFill the template and upload it, or type straight into the tool. Your work saves as you go.
Stage 5 of 5
Read and share the resultRead the headline results, then print or save the PDF report.
SIPOC: how the agent works
Who supplies what, what goes in, what the agent does, what comes out, and who uses it.
| Suppliers | Inputs | Process | Outputs | Customers |
|---|---|---|---|---|
|
|
|
|
|
Input data it needs
Everything the agent asks for, in the order it asks. Columns marked "worked out" are calculated for you; you only fill the rest.
| Data | Unit | What to enter |
|---|---|---|
| Which product is being forecast? | Name one product or product family with similar demand. Mixing items with different patterns spoils the fit. | |
| Periods ahead to forecast | periods | How many periods after the last one in the history you want the forecast for. Use 1 for the next period. |
| Supplier lead time | periods | Time from placing an order to receiving it, in the same period unit as the history. A fraction is allowed. |
| Service level target | % | The share of replenishment cycles in which you want no stock-out, for example 95. Between 50 and 99.9. |
| Annual demand | units per year | Total units expected in a year, used to size the order. Use your forecast scaled to a year if you have no better number. |
| Cost of placing one order | ₹ per order | Everything an order costs regardless of size: purchase processing, freight per shipment, inspection. |
| Cost of one unit | ₹ per unit | What a unit costs you to buy or make, used to value the stock you hold. |
| Holding cost rate | % of unit cost per year | Yearly cost of keeping stock as a share of its value: capital cost, storage, insurance and obsolescence. 15 to 30 is common; use your own. |
| Demand by periodtable | One row per period in time order, numbered 1, 2, 3 and so on with no gaps. Use actual units sold or shipped; where a stock-out hid demand, use the demand you could not meet. Columns: Period number; Demand (units); Period x demand (worked out); Period squared (worked out); Demand squared (worked out); Trend line (worked out); Actual minus trend (worked out). | |
| Which stock policy did you adopt, and why? | Write the reorder point and order quantity chosen, the service level, and what would make you revisit them. | |
| Actions for the next 90 daystable | List the first actions in order. Give each an owner by role, a measure that shows it worked, and when it starts. Columns: Action; Owner (role); Measure of success; When. |
Try the demo
See a complete run on a fictional company before you enter anything of your own. No account, no AI, nothing saved.
Demo · sample, not real
A fictional adhesive distributor sold 100 packs in its first month and 151 in its eighth, with a steady upward drift. It needs a stock policy for packs bought from a supplier with a two-month lead time.
Provide and update your data
- Open the pilot and choose Download blank Excel template, or Download sample to see a filled example.
- Fill the template with your own data and use Upload to load it; or type straight into the page. Both give the same result.
- Your work saves automatically while you type, so you can come back and change any figure; results update at once.
- To refresh: Add the latest period to the history every cycle and rerun; compare last forecast with actual sales.
The pilot is being reviewed and opens to clients once it is approved.
What you get back
Headline results
- Forecast demand (units in the target period)
- Safety stock
- Reorder point
- Economic order quantity
Working figures shown beside them
- Periods of history used
- Trend: change in demand per period
- Trend line value at period 0
- Standard error (typical miss)
- R² (how much the trend explains)
- How good is the fit
- Service factor z
- Orders per year at the economic quantity
- Ordering plus holding cost per year at EOQ
In what form
- Results at a glance on the page, updating as you type. Available
- PDF report in the standard Eccellere layout, from Print / PDF on the tool page. Available
- Dashboard over time that keeps each run and charts the change between runs. Planned
The agent never lets AI invent a number: every result comes from the formulas below, and any AI writing is labelled and editable.
Method and limits
Based on
Least-squares regression (Legendre, 1805; Gauss, 1809); economic order quantity (Ford W. Harris, 1913); safety stock under normal demand (standard inventory theory) (1805 to 1913).
A trend line summarises where demand is heading, the scatter around it measures uncertainty, and the stock policy buys protection against that uncertainty at a chosen service level.
Use it when
Use it when you have at least six regular periods (weeks or months) of demand for one product, demand moves with a steady trend, and you must decide how much to stock and when to reorder.
Do not use it when
Do not use it for a new product with little history, for strongly seasonal products (the straight line ignores the season), or for demand driven by a few large orders; it will understate the swings.