Advanced Analytica Advanced Analytica: IBOM
← BACK
Energy technology: A governed product catalogue for agent-assisted sales — Structuring more than 900 products, variants, images, approvals, and brand rules so sales agents can build accurate customer materials.

Energy technology: A governed product catalogue for agent-assisted sales

Advanced Analytica
Share

Structuring more than 900 products, variants, images, approvals, and brand rules so sales agents can build accurate customer materials.

Making sales materials right by construction

This anonymised case study shows how an off-grid power company prepared its product and brand knowledge for agent-assisted sales. The business supplies power systems for vehicle and marine applications. Its sales team creates product packs and quotations for individual enquiries, drawing from a catalogue with more than 900 products, many variants, technical specifications, pricing ranges, and approved images. The work must also follow the company’s brand book, including rules governing how products are named and presented.

We transformed the online catalogue into a governed product-data store and structured the relevant brand guidance alongside it. An agent can request a product and receive the approved specification, correct variant information, primary image, and relevant brand context together. The objective is not to generate a plausible sales pack and correct it later. It is to make the approved ingredients available from the start, so the output is right by construction.

The challenge

Building a tailored pack or quote required salespeople to combine information from catalogue pages, product variants, image links, and brand guidance. That created several risks:

  • outdated or incomplete specifications could enter customer material;
  • the wrong SKU, weight, price, or image could be selected;
  • website changes or broken links could remove an approved asset;
  • product presentation could drift from brand rules; and
  • no single record showed source, approval, rights, and current status.

The company needed its product knowledge to become dependable operational data rather than information reconstructed for every enquiry.

Building the governed catalogue

We structured more than 900 products into machine-readable records. Each includes its approved name, description, product type, tags, availability, and price range. Beneath each product sit its variants, carrying their own SKU, price, and weight.

Images are part of the governed record rather than external references. Every product can hold multiple images with alt text, display position, and an explicitly marked primary image. Storing approved assets inside the governed system means a website redesign or broken source link does not remove the image required for customer work.

Approval and provenance travel with the data

Each product record is approved by a named person. Provenance records when the information was captured, who approved it, the rights note attached to it, and a content fingerprint showing whether the underlying material has changed.

Governance becomes part of the product object itself. An agent does not receive a specification first and then search elsewhere to determine whether it can be trusted. The evidence and approval status arrive with the content.

Connecting products to brand guidance

The brand book was structured alongside the catalogue. Approved product images and presentation choices can be tied to the section of the guidance governing their use, such as a website product page or customer-facing sales pack.

That connection gives an agent more than product retrieval. It provides the technical facts, approved visual asset, and presentation context required for the task in one controlled response.

The operating workflow

When a salesperson or agent requests a product, the system can return:

  • the current approved product record;
  • the appropriate variant and SKU;
  • relevant price and weight information;
  • the approved primary image and its metadata;
  • provenance and approval status; and
  • the brand rules governing how the product should be shown.

Nothing has to be assembled from unverified search results, and unapproved material does not need to reach a customer before it is caught.

Outcome

The company now has a governed foundation for generating accurate product packs and quotations. Sales teams can retrieve the correct ingredients faster, while the organisation retains control over which data, images, and presentation rules enter customer-facing work.

The architecture also makes change manageable. Products, variants, prices, assets, and guidance can be updated as governed records without rebuilding the entire sales workflow.

What this case study demonstrates

Reliable agentic creation starts with governed source material. When product data, assets, approval, provenance, and brand context are structured together, an agent can create from approved facts instead of generating first and relying on people to find every error afterwards.

Start The Conversation

Find out where this case study can create value in your business.

This case study shows how agentic AI can turn knowledge and process into a controlled workflow. The useful next step is to identify where the same pattern applies inside your own processes, which controls need to be explicit, and what evidence is needed before agents move into production.

We turn that into a practical route from opportunity to governed agentic AI in production.

Related Case Studies

View All
Advanced Analytica

Most businesses are sitting on information they can’t use at speed. The people who hold it are busy, and when they leave, the knowledge goes with them. The documents are static, and the processes around them weren’t designed for AI.

Advanced Analytica works with these businesses to turn that information into structured data assets. Once they're integrated, AI systems can govern it, and the business can use it. We bring in the strategy, the specification and the AI skills to rework how the business operates.

MOVE FAST. STAY SAFE.