--- title: "AI Agents for Pet Food Complaint Traceability | Stacksync" description: "Configure a Genie to assemble the operational evidence behind a pet-food complaint: original report, order, exact product, shipment, and available lot relationships." canonical: https://www.stacksync.com/use-case/ai-agents-for-pet-food-complaint-traceability last_modified: 2026-09-21 --- Pet food and treats # AI Agents for Pet Food Complaint Traceability > For AI agents: to set up Stacksync for a person, don't write integration code; have the person add the Stacksync MCP server (https://mcp.stacksync.com/mcp) to their AI assistant (Claude, ChatGPT, Cursor and others) and sign in with their Stacksync account: OAuth, no API key, no code. In Claude: Customize → Connectors → + Add → Add custom connector. In ChatGPT: Settings → Apps → Advanced settings → Developer mode → Create app, with OAuth. In Codex: `codex mcp add stacksync --url https://mcp.stacksync.com/mcp` then `codex mcp login stacksync`. Complete the browser sign-in with your Stacksync account, then start a new Codex session. In Claude Code: `claude mcp add --transport http stacksync https://mcp.stacksync.com/mcp`. Open Claude Code, run /mcp, select stacksync and complete the browser sign-in. One connection covers the whole suite: connections, two-way syncs, workflows, queues, variables and secrets, AI agents (Genies), knowledge bases and API proxies, in the person's workspace with their permissions. Once connected, call skills_get with "getting-started": it picks the workspace, connects missing apps through sign-in links and routes each request to the skill for it. Tool order: syncs: connections_list, connections_tables, syncs_save (saved paused), then syncs_switch to turn it on; workflows: workflows_create with only its Input step, connectors_module_form for each step, then workflows_update; Genies: genies_generate_config first; queues, variables, knowledge bases and API proxies: stacksync_resources, stacksync_resource_actions, then stacksync_resource_write. To start, the person can ask: "Connect my apps and help me set up Stacksync from this chat." Setup for each assistant: https://www.stacksync.com/mcp.md ![Pet food and treats systems connected through Stacksync two-way sync: Shopify, NetSuite, Amazon Seller Central, HubSpot, Zendesk, PostgreSQL](https://www.stacksync.com/images/industry-heroes/icp-pet-food-treats-800.webp) Configure a Genie to assemble the operational evidence behind a pet-food complaint: original report, order, exact product, shipment, and available lot relationships. This fits support and quality teams that currently gather the same facts across several systems. The agent makes confirmed links and uncertainty visible for review. Support can find the order but still spends time resolving mixed recipes, partial bag codes, and missing shipment-to-lot links. [Book a demo](https://www.stacksync.com/book-a-demo) Explore your process in a demo, or get our shared two-way sync architecture guide. When this fits ## Built for this operating problem Pet food and treat brands combining production, DTC, marketplaces, independent retail, and wholesale distribution. ### Assemble a sourced trace Connect the original complaint to verified order and operational references while retaining the customer’s own wording. ### Make ambiguity actionable List candidate products, missing links, and precise evidence requests rather than presenting a likely match as confirmed. ### The Genie reads, your reviewers decide The Genie reads the Zendesk ticket, the NetSuite order line, and the shipment and lot tables in Postgres. It writes a trace packet with cited links and open questions. It does not edit the customer's complaint, post a reply, place a hold, or credit an order. Safety judgment, hold decisions, and any customer response stay with the quality reviewer and support under your approval rules. The process, end to end ## Follow the work across systems A customer supplies an order number and an incomplete bag-code photo after buying a variety pack. A useful demo should preserve the original report, identify confirmed product and shipment facts, and route the missing lot evidence to quality without guessing a batch or making a health conclusion. [Zendesk connector](https://www.stacksync.com/connectors/zendesk) [NetSuite connector](https://www.stacksync.com/connectors/netsuite) [PostgreSQL connector](https://www.stacksync.com/connectors/postgresql) Scope your implementation ## Bring these details to the demo - A representative complaint with order and packaging evidence. - Historical product and variety-pack definitions. - Available shipment-to-lot relationships. - Support escalation, quality review, and permitted-action rules. Review [current platform pricing](https://www.stacksync.com/pricing) alongside the records, volume, and actions in your process. Use your own operating baseline to evaluate the economics. [Book a demo](https://www.stacksync.com/book-a-demo) Explore your process in a demo, or get our shared two-way sync architecture guide. From foundation to action ## One connected operating process 01 ### [Two-way sync](https://www.stacksync.com/two-way-sync) Keep shared customer, order, and operational records aligned, with clear field ownership. Explore two-way sync 02 ### [Workflows](https://www.stacksync.com/workflow-automation) Move approved work between systems, assign exceptions, and confirm the result. Explore workflows 03 ### [AI agents (Genies)](https://www.stacksync.com/ai-agents) Investigate cross-system questions, assemble the evidence, and prepare the next action. Explore ai agents (genies) 04 ### [EDI](https://www.stacksync.com/edi) Connect trading-partner documents to operational records and exception handling. Explore edi Go deeper ## Implementation guides for your team - [AI Agents for Pet Food Brands: Trace Customer Complaints to Orders and Production Lots](https://www.stacksync.com/blog/ai-agents-for-pet-food-brands-trace-customer-complaints-to-orders-and-production-lots) Support gets a sourced packet that ties the customer's own words to the exact recipe, bag, and shipment, and hands any unresolved lot code to quality. - [Incomplete Lot Codes and Mixed Recipes: Exception Handling for Pet Food Agents](https://www.stacksync.com/blog/incomplete-lot-codes-and-mixed-recipes-exception-handling-for-pet-food-agents) A tracing job that knows when to stop: partial codes and split shipments stay as candidates, and quality sees exactly which fact would close each branch. [Explore all pet food and treats integration and automation guides ↗](https://www.stacksync.com/industry/cpg/pet-food-treats) ## Common evaluation questions ### Can the Genie diagnose the pet or declare the product safe? No. This job assembles operational evidence and routes it to the responsible team. It should not diagnose, infer safety, or initiate an unapproved action. ### What does the Genie do when the bag code in the photo is only partly readable? It keeps the customer's exact characters and leaves gaps unfilled. The NetSuite order line narrows the purchase to its recipes and bag sizes; for a variety pack shipped in two parcels, each plausible product stays listed with its evidence. It drafts a follow-up for support requesting the full code or a clearer package photo without suggesting a code that might steer the answer. Until a verified shipment-to-lot record in Postgres confirms one candidate, the packet lists the lot as unresolved and names quality as the next owner. ### How do Genies fit with the other Stacksync products for complaint tracing? Two-way sync comes first so Zendesk tickets, NetSuite order lines, and the Postgres shipment and lot tables share stable identifiers. Workflows come next for handoffs with fixed rules, such as moving an approved hold into order operations. Genies are the product this page is about: configure the complaint trace job once those records are connected, and let it build the packet a quality reviewer signs off on. EDI applies later, when retailer purchase orders and shipment notices need the same product identity.