DwyerOmega Onboards an Acquired Product Series in 40 Minutes With Akeneo MCP

An industrial manufacturer with product models that run to 200,000 permutations put the Model Context Protocol on top of its PIM, and the result a commerce team can measure is 82 acquired product series loaded in about 40 minutes each, with a read-only Power BI view of catalog quality and a human still approving every change.

What is the gap, for a manufacturer that buys companies, between closing an acquisition and getting the acquired product line in front of customers and sales teams? At DwyerOmega, a maker of sensing, monitoring and control products that manages multilingual content, frequent acquisitions and millions of possible configurations, the answer has come down to about 40 minutes per product series. Akeneo is publishing the second part of its customer story on the company on November 4, and shared the draft with Talk Commerce ahead of time. Part 1, by Samira McDonald, Senior Customer Marketing Manager at Akeneo, covered how DwyerOmega rebuilt its product data pipeline with Akeneo MCP so that the PIM feeds Microsoft Fabric, Power BI, SharePoint and AWS without a development-heavy integration. Part 2 is about what the company does with the data once it moves.

Cyrus Grimes, Director of Product Content Management at DwyerOmega, is the voice through both parts.

Catalog Quality as a Power BI Report

With the MCP pipeline in place, product management and marketing teams get a filterable view of catalog quality in Power BI. The dashboards show whether products meet their targets for hero and variant-level images, 360-degree spins, image alt text, short and long descriptions, unique SKU-level descriptions, accessories and product relationships, CAD files, upsell and cross-sell assignments, and SEO titles and metadata. A user can filter by product manager or product model, see where content misses its target, and export a list of the products that need work.

The dashboard is read-only on purpose. When McDonald asked whether edits in Power BI push back into the PIM, Grimes answered, “No, this is just a report.” Updates are still made in Akeneo or through coordinated loading documents handled by trained PIM users.

“A Product Manager was able to understand exactly where he needed to go. When he clicks this, he gets this list of product series, and he can just export that and work on those directly. He didn’t have the tools to do that before.”

Before the dashboard, inconsistencies surfaced through customer complaints, manual website checks or one-off investigations. The draft says data quality work had been easy to push aside because the company is in an acquisition phase rather than a maintenance phase, and the dashboard makes the work visible and assignable. Two further ideas are in exploration rather than production, a data hygiene view that compares records across the source system, SAP Commerce Cloud and Akeneo to find synchronization gaps, and an AI-assisted workflow that reads product data issues reported in a team chat channel, checks Akeneo, and proposes corrections through MCP with a person approving each one.

Spec Sheets Into Product Descriptions

DwyerOmega is also running a multi-phase, AI-assisted workflow built in Claude to improve product descriptions. Many technical products have capabilities documented in specification sheets and manuals but are represented online by a small set of popular variants, and the older descriptions were thin.

“We had some product descriptions that were pretty weak. Literally just a paragraph, and kind of just marketing fluff.”

The workflow uses Akeneo product records to locate the relevant manuals and spec sheets, runs local optical character recognition through a local language model to extract the technical content, applies quality control, builds structured capability-led descriptions, and merges them with the useful parts of the existing copy before product managers review and load them back into Akeneo. Grimes reports that keeping the existing content in the merge has helped organic search traffic stay stable and growing against broader industry declines.

The Acquisition Workflow

Grimes names acquisition onboarding as the use case with the most potential. Newly acquired businesses do not organize or sell products the way DwyerOmega’s established catalog does, and some products are technical, expensive, or configurable across more permutations than a cart can handle.

“Not everything is easy to add to your cart and sell there. They might be extremely expensive or very technical, and we do not want the customer to just spend $10,000 and be like, ‘I got the wrong thing’.”

For those products DwyerOmega created a sales-assisted product family, where the button asks the buyer to contact a salesperson rather than add to cart, while the product information is still managed and published in full. The MCP workflow chains the systems together. A web scrape of an acquired company’s product series loads supporting assets into SharePoint, mirrors images into AWS for web delivery, creates the asset in Akeneo with the URL populated, and builds the product series with a placeholder variant and basic information.

“We’re able to get the assets, the product images, spec sheets, manuals, and load this simple product model into Akeneo in 40 minutes. We’ve got 82 of them so far. It’s been going pretty fast, and we’ve only been doing it for a couple of weeks.”

The company no longer has to wait for every commerce decision to be final before an acquired product line is useful to customers and sales teams.

What This Means for Commerce Teams

Three things in the DwyerOmega story travel to a retailer or brand that is not an industrial manufacturer. The first is the read-only dashboard, which gives marketing and product teams a list to work from without giving them a second place to edit product data, so the PIM stays the one source. The second is the sales-assisted product family, a catalog structure for products a merchant wants findable but not purchasable in a cart, which applies to any configurable or high-ticket line. The third is the operating rule under the whole thing, which the draft states plainly, automate the repeatable discovery and preparation and keep people in control of consequential updates.

The figures are DwyerOmega’s own, as told to Akeneo for a vendor customer story, and Talk Commerce has not seen the dashboards or the workflows run. The 40 minutes and the 82 series describe the simple product model with a placeholder variant, which is the start of an onboarding and not the finished catalog entry. Akeneo’s Part 1 has the pipeline detail, and Part 2 publishes on akeneo.com on November 4.