Customers, employees, and buyers reach grounded answers and product decisions by describing what they need.
Coveo Merchandising Agent
Merchandisers act on performance questions without leaving their workspace, and nothing the agent proposes applies without approval.
A conversational agent inside Coveo Merchandising Hub that turns plain-language requests into rules, bulk changes, and performance answers.
What the agent does
Investigates performance questions and drafts rule, bulk, and cross-storefront changes on its own, then holds each one for explicit approval.
- Built by
- Coveo, which builds and runs the agent inside its own merchandising hub
- Contributed by
- Coveo (Merchandising agent for search, listings, and recommendations)
- Industry
- Retail, Cross-industry, Grocery, Automotive, Healthcare
- Audience
- B2C
01
The problem
Why this exists
Merchandising work is spread across search, product listings, and recommendation slots. A single rule means finding the right screen, picking the condition, and then repeating the same setup for every brand, region, and storefront that needs it, with the local variations each one requires.
Read more
The work that goes undone is the long tail. Searches and listing pages outside the top performers rarely get a second look, because reading their performance data takes as long as making the change, and high-volume edits arrive as spreadsheets and manual repetition.
A conversational assistant that only answers questions leaves that configuration work in place, and an agent that changes what shoppers see without sign-off is a risk merchandising teams will not accept.
02
Outcomes
What changes when this is in place
- Merchandisers start from intent rather than configuration steps, working in natural language inside the workspace they already use every day.
- Teams can work beyond their top-performing searches and listing pages, so small long-tail improvements add up.
- Every change is reviewed and approved before it is applied.
03
How it works
Architecture
The agent runs inside the merchandising workspace and works through the platform's commerce capabilities. It interprets the merchandiser's request, checks the organization's configuration and performance data, and prepares the supported changes as a plan for approval instead of applying them.
Read more
Rules can be created, updated, and replicated across search, listings, and recommendations for the brands, regions, and storefronts the merchandiser names, and high-volume changes are prepared in bulk rather than repeated by hand. Each proposed change requires explicit approval before it takes effect, the agent never deletes anything, and the rules it does create are tagged so they can be found, edited, or removed later.
It acts within each user's existing permissions in the workspace, so the agent cannot reach further than the merchandiser operating it.
Tech stack
Coveo Merchandising HubCoveo Commerce APICoveo Merchandising Agent
Resources
Next step
Request an intro
Coveo is behind this solution. Ask about putting merchandising changes within reach of plain language, and the MACH Alliance will put you in touch with the person who can answer.
Not ready to talk to anyone? MACH Insider is the Alliance mailing list. New solutions, program openings, and the research behind them, once a month.
Everyone credited on this solution
- CoveoMerchandising agent for search, listings, and recommendations
Every organization named here has a page listing the rest of its work on the Hub.
Related solutions
Make products easier to find, compare, and buy by completing the catalog details that search engines and AI assistants need.
Agentic Product Data Enrichment
Shoppers see relevant products from sister brands without being redirected off the site they are on.
Athena AI Cross-Brand Recommender
AI Exchange Hackathon
Verification
Published case study
The detail on this page is drawn from a case study published by the contributor or the MACH Alliance. Any figures on this page are the ones that case study states.
What this page does not establish
- Measured customer outcomes are not published: the agent reached general availability on Oct 28, 2026.
- The submission names no customer, so no deployment, storefront, or team size is established here.
Where this came from
Solution detail is drawn from Coveo's submission to the hub, a Merchandising Agent overview dated Oct 28, 2026.
Status: Live in productionAdded Oct 29, 2026A listing is an editorial decision, not a MACH Alliance certification.
Built something worth showing?
Put your agentic solution in front of the enterprise leaders who use the hub to decide what to build next. Submissions are open to MACH Alliance Members, Collaborators, or Ambassadors.