Chef AI, the AI assistant in beCPG PLM
Your R&D team is not there to re-key supplier specification sheets. Your quality team is not there to dig through folders looking for last year’s customer specification.
Chef AI takes care of it. It is the assistant built into beCPG PLM: you ask your question in plain language, it works on your own product data with your access rights, and it makes proposals. You decide.
Values read from the specification sheet, for you to check and validate| Allergen | Brought by | Recipe |
|---|---|---|
| Gluten | Flour MP96803 | Pastry cream |
| Milk | Milk MP96796 | Choux pastry |
| Soy | Chocolate MP96805 | Glaze |
One question, one answer drawn from your data
Ask your question from the product, project or document you are working on. Chef AI calls the beCPG tools it needs and tells you which one it used.
- Search and compare: products by name, code or property, the Nutri-Score of two trials, the products that meet a brief.
- Analyze and optimize: a multi-level composition tree with costs, a recipe cost optimized under your constraints, your business intelligence queries.
- Projects and workload: priority tasks, schedules, a team member’s workload.
- Regulatory questions and checking a product’s compliance.
- Documents: read a supplier specification sheet to pre-fill a raw material, query a PDF, compare an artwork proof with a customer specification.
- Create products, raw materials, projects or packaging from a brief.
Answers come back in the language you choose.
What your teams no longer do
Re-keying supplier specification sheets
Drop in the PDF: Chef AI reads the values and pre-fills the raw material. You check and validate.
Searching
“Which finished products contain palm oil?” The answer covers your whole portfolio, without building a query.
Writing the first draft
Names, descriptions, marketing copy, translations, sensory profiles: proposed, then refined by the person who knows.
Checking by hand
Spelling, missing fields, allergens to declare, label consistency: flagged in the product’s Suggestions panel.
Comparing documents line by line
Chef AI compares an artwork proof with the customer specification and lists the differences to review.
Redoing the same calculation
Cost breakdowns, composition trees, a cheaper recipe under constraints: requested in one sentence, calculated by the beCPG engines.
AI proposes, your experts validate
On every product and every document, the Suggestions panel lists what Chef AI proposes: values read from a document, fields to complete, translations, allergens, label review.
You accept them one by one or all at once. Nothing is saved in the PLM without your confirmation, and an accepted change is traced like any other change in beCPG.
Accepted one by one or all at once
Values calculated by the beCPG engines from the formulaWhat it never does
It does not decide what goes on your label.
Nutritional values, Nutri-Score, ingredient and allergen labeling, CLP classification, cost optimization: the beCPG engines calculate them, as they have for years. Same data, same result, every time, including six months later in front of an auditor.
If an AI answer and a calculated value differ, the calculated value prevails.
Your suppliers get help too
In the new supplier portal, AI reads the specification sheet uploaded by the supplier, proposes the values and allergens, cross-contamination included, and flags what has changed since the previous version.
The supplier applies each proposal. Your quality team validates the sheet as usual.
Cross-contamination read from the sheetUse your own assistant
Claude, Gemini or the agent your IT department is building can work on beCPG data through the MCP server, with each user’s access rights.
Connect your AI assistantStay in control
Which calculations use AI, where your data goes, who validates each change and how it is traced.
AI governanceSee it on your products
A 30-minute demo on your own products is usually enough to tell whether it fits the way you work.
Talk to a PLM expertThey develop their products with beCPGSee all our customer references
Which AI model does Chef AI use?
Chef AI is built on Google Gemini. Chef AI works on your beCPG data with the access rights of the user asking the question.
Is Chef AI included in beCPG?
Chef AI is an optional beCPG module, activated at your request.
Can Chef AI change my data without me?
No. In beCPG, every creation or change proposed by Chef AI is a suggestion: nothing is saved until a user has confirmed it, and accepted changes are traced like any others.
Does Chef AI calculate my labels?
No. Nutrition, Nutri-Score, labeling, CLP and costs are calculated by the beCPG engines from your formulas. Chef AI helps you search, read, write and check.
Can it be installed on our own servers?
Yes. The AI module installs with an on-premise beCPG. It connects to the Google Gemini AI service.
Does beCPG train AI models on our data?
No. beCPG does not use your data to train AI models.
See Chef AI on your own products
Bring a supplier specification sheet and a product: we will show you what Chef AI proposes.
