Manufacturing
Which products are actually most profitable?
The best-selling product and the most profitable product are often not the same one, once real production cost and capacity are accounted for. FactSmith ranks products by margin, not volume, so the answer reflects what is actually worth making more of.
Why this matters
Volume-based reporting is usually what is easiest to pull, so profitability by product tends to get calculated occasionally rather than continuously -- and decisions get made on the wrong number in between.
What data is needed
Product-level sales and production or material cost facts, ideally down to the batch or work-order level.
The evaluation copy runs against PostgreSQL. SQL Server is on the adapter path for a customer warehouse; that path is not what the package proves end to end today.
How the analysis works
Realised margin per product is computed using actual cost, not standard or list cost, where the data supports it, and ranked by rand contribution as well as percentage.
What can go wrong
Shared costs across product lines -- a shared production line, for instance -- can distort per-product cost if allocation is not consistent. A low-margin product that enables a high-margin one needs a human call, which is what vouching a fact is for.
Example
A manufacturer asks which products earned the most gross margin last quarter, not just the most revenue. Ask returns the ranked list with both figures shown.
How FactSmith approaches it
Ask is what is available now. Easy Data -- turning messy sources into that dimensional foundation -- is in early development.
FactSmith calls this the Fact Layer: a data integration (ETL) step, a knowledge base, and a business ontology, working together underneath the answer. On screen it stays simple -- ask a question, get a trusted answer -- with the layer-by-layer detail available to anyone who wants to see how the answer was built.
Permissions are enforced beneath the AI, not by it -- see Trust and security.