Skip to content
New: The Agent Solutions Hub is live. Explore real agent use cases

Snag Product Operations Agent

More than 14,000 products updated in one run, and one of Snag's fastest launches, live in about two weeks.

Request an intro

Snag's team asks Claude in plain language, and Patchworks carries the work out across six Shopify stores, a PLM platform, and five warehouse systems.

What the agent does

Takes a plain-language request, picks the flow to run, and carries out bulk product updates and store-by-store syncs across Snag's systems.

Brand
Snag
Built by
Snag's technology team, on Patchworks
Contributed by
Patchworks (Integration platform and MCP server)
Industry
Retail, Apparel & Footwear
Audience
B2C
Category
Integration & OrchestrationCommerce & Ordering
01
The problem

Why this exists

Snag sells size-inclusive tights and clothing in more than 100 countries. More than 12,000 active SKUs run through six Shopify storefronts, five warehouse management systems, a PLM platform that holds the master product record, Sage 200 for finance, and more than a dozen ad catalogs. By Snag's own estimate, moving product and order data between them took about 70% of its technical team's time.

Read more

In early 2026 Snag connected Claude to Shopify and its data warehouse through native MCP connectors, and hit three limits. Vendors expose less through MCP than through their APIs, so bulk operations were blocked. Six stores meant constant re-authentication. Routing large data volumes through the model's context slowed everything down. The PLM platform had no MCP server at all.

02
Outcomes

What changes when this is in place

  • More than 14,000 products updated in a single operation through Shopify's Bulk Operations API, which Shopify's own MCP server does not expose. Jobs that took hours now run in minutes.
  • 10 to 12 connectors built by Snag's own team, including the PLM platform and a warehouse system with no AI connector. Most went live within hours. The hardest took two days.
  • One plain-language request syncs a product to exactly the storefronts named, with market-specific changes applied, instead of an always-on sync across the whole catalog.
Read more
  • One of Snag's fastest product launches to date, live in around two weeks.
  • No consultancy or front-end development spend to stand up the new processes.
03
How it works

Architecture

Claude is the orchestration layer. It interprets the request, holds the business logic and transforms the data in natural language. Patchworks is the execution layer. It runs each call against the target system's API and returns the result.

Read more

Flows are deliberately simple, usually three steps: receive the call, execute it against the target system, return a response. The payload passes straight through, so most flows need no field mapping.

Heavy data never enters the model's context. Claude triggers the operation and Patchworks moves the data, which is what made a 14,000-product update practical.

Snag chose Patchworks because it was the only shortlisted integration platform with a working MCP integration, so the platform itself is operated through Claude rather than a separate interface.

A Snag team member makes a plain-language request to Claude, the orchestration layer, which holds the business logic and transforms the data. Claude calls Patchworks over the Model Context Protocol. Patchworks is the execution layer: a pass-through flow receives the call, executes it, and returns the response, so heavy data moves through Patchworks rather than through the model. It reaches six Shopify storefronts, Shopify's Bulk Operations API, which Shopify's MCP server does not expose, a PLM platform with no MCP server of its own, warehouse management systems, and Sage 200 and other systems.

A Snag team member makes a plain-language request to Claude, the orchestration layer, which holds the business logic and transforms the data. Claude calls Patchworks over the Model Context Protocol. Patchworks is the execution layer: a pass-through flow receives the call, executes it, and returns the response, so heavy data moves through Patchworks rather than through the model. It reaches six Shopify storefronts, Shopify's Bulk Operations API, which Shopify's MCP server does not expose, a PLM platform with no MCP server of its own, warehouse management systems, and Sage 200 and other systems.
Open standards used
Model Context Protocol (MCP)REST APIs
Tech stack
ClaudePatchworks integration platformPatchworks MCP serverShopifyShopify Bulk Operations APICentricPlytixLinnworksShipBobAirtable
Get hands-on

Resources

Published case study
Next step

Request an intro

Patchworks is behind this solution. Ask about connecting AI agents to the systems you already run, and the MACH Alliance will put you in touch with the person who can answer.

The MACH Alliance passes your details to a named contact at Patchworks who knows this work and can answer your questions. We aim to reply within 2 business days. Your details are handled under the MACH Alliance privacy policy.

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.

Join MACH Insider

Everyone credited on this solution

Every organization named here has a page listing the rest of its work on the Agent Solutions Hub.

Keep reading

Related solutions

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.

Where this came from

Published from the winner's case study and the 2026 MACH Impact Awards announcement. Solution detail is drawn from the Patchworks case study on Snag, which Patchworks submitted to the Agent Solutions Hub.

Status: Live in productionAdded Oct 20, 2026A listing is an editorial decision, not a MACH Alliance certification.
Put a solution forwardBack to the Agent Solutions Hub

Built something worth showing?

Put your agentic solution in front of the enterprise leaders who use the Agent Solutions Hub to decide what to build next. Submissions are open to MACH Alliance Members, Collaborators, or Ambassadors.

Put a solution forward