Skip to main content

AI-assisted creation

Five Inventory modules carry a …createwithai permission, and there are seven distinct AI surfaces between them. They are documented together because they share one shape.

ModulePermissionSurface
Units of measureGenerate Unit of Measurement using AIAI Suggestions
CategoriesGenerate Product Category With AIAI Suggestions
AttributesCreate Attributes with AIAI Generate
Raw materialsGenerate Raw Materials with AIAI Suggestions + Review AI queue
ProductsGenerate Product with AISuggestion, metadata, description and image generators

1. The shared shape​

Nothing is written blind. Every generator stages its output for review; you approve what you want. The staging area differs by module — raw materials get a durable queue, products get staging_products, the rest review inline.


2. Three gates decide whether AI is available at all​

An AI utility appears only when all three are true:

GateWhere it livesMeaning
is_activeThe platform's AI utility catalogueThe utility is switched on globally
Package entitlementai_utility_packages, per organisationYour plan includes it
is_implementedComputedThe code path exists

On top of that, the operator needs the module's …createwithai permission.

A missing AI button is usually entitlement, not permission

If the button is absent for an org owner, check the package before checking the role. The three gates are described in full in the operator documentation for AI utilities.


3. Credits​

Every generation spends credits. The cost is per call and set per utility, so a product image costs more than a list of units.

Generate is not a preview

There is no dry run. Clicking Generate spends the credit whether or not you keep the output. Fill the inputs properly first — a vague business description produces a vague list you will discard at full price.


4. Target languages — the pattern worth understanding​

Most generators offer a language chip set. The rule is stated on the modal itself:

English is generated first as the canonical list. Other languages are translated from it.

Figure 1 — The raw-material generator. English is required; the rest are translations of it.
EnglishRequired, always selected, and generated first
Everything elseTranslated from the English output, not generated independently

Twenty-three languages are offered — Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Punjabi, Kannada, Malayalam, Odia, Urdu, Assamese, French, Spanish, German, Italian, Portuguese, Japanese, Chinese, Korean, Arabic and Russian.

Generating a language the module cannot display

The list screens offer a Language Context of Bengali / English / Hindi only. Generating Korean names stores them and shows them nowhere in Inventory. They are still readable through the external API.


5. Writing a good prompt​

Every generator asks for a description of the business. The reference tenant's inputs show the level of detail that works:

FieldExample
Business typeCloud Kitchen - Speciality Bengali and North Indian
Finished product list"All Bengali speciality Foods, starting from Sukto to Mutton Biriyani, including Sweet Dishes, Moglai Partha, Sea Foods like Crab Prawn, Fish Like Hilsha, Bhetki, Bengali Speciality Deserts, Luchi, Radhaballavi and many more"

Naming the outputs is what produces useful inputs. "Restaurant" yields a generic pantry list; naming the dishes yields the ingredients those dishes need.


6. Where to go next​

Generating catalogue recordsUnits, categories and attributes — the shared modal
Raw material suggestionsThe durable review queue
Generating productsProducts, metadata, descriptions and images