--- title: "AI Agents for Household Product Quantity Disputes" description: "Configure a Genie to investigate refill, multipack, and case-quantity disputes using approved product relationships and actual shipment evidence." canonical: https://www.stacksync.com/use-case/ai-agents-for-household-product-quantity-disputes last_modified: 2026-09-21 --- Household consumables # AI Agents for Household Product Quantity Disputes > 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 ![Household consumables systems connected through Stacksync two-way sync: Shopify, NetSuite, Amazon Seller Central, Salesforce, Zendesk](https://www.stacksync.com/images/industry-heroes/icp-household-consumables-800.webp) Configure a Genie to investigate refill, multipack, and case-quantity disputes using approved product relationships and actual shipment evidence. This fits teams that manually reconstruct unit conversions before responding to distributor claims. The output is a reviewable comparison and a precise list of missing facts. The customer, invoice, and warehouse use different units, making a simple shortage claim expensive to investigate. [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 Cleaning, paper, refill, and household-consumable brands combining manufacturing, marketplaces, DTC, and wholesale distribution. ### Compare like quantities Preserve each source unit and apply only approved product and pack relationships. ### Prepare an evidence-based case Return cited shipment and order facts, reproducible calculations, and unresolved gaps for finance review. ### No credits, no definition changes The Genie reads the claim from the Gmail thread, the sold-pack definition and shipment evidence from NetSuite and Postgres, and stops there. It does not post a credit memo, edit a pack definition, or reply to the distributor. A missing or conflicting conversion halts that calculation and becomes a question for product operations. Accounts receivable and finance decide the remedy from the packet. The process, end to end ## Follow the work across systems A distributor reports missing cases while the warehouse recorded individual refill packages. A useful demo should show original quantities, the approved effective conversion, and the resulting comparison. It should also show that an unknown pack factor stops the conclusion and creates a question for product operations. [NetSuite connector](https://www.stacksync.com/connectors/netsuite) [PostgreSQL connector](https://www.stacksync.com/connectors/postgresql) [Gmail connector](https://www.stacksync.com/connectors/gmail) Scope your implementation ## Bring these details to the demo - A real quantity dispute with order and shipment references. - Approved refill, multipack, and case conversions. - The owners of product definitions and claim decisions. - Rules for credits, external responses, and uncertain evidence. 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 Household Brands: Investigate Refill and Case-Quantity Disputes](https://www.stacksync.com/blog/ai-agents-for-household-brands-investigate-refill-and-case-quantity-disputes) A quantity-dispute Genie lines up cases, multipacks, and loose refills with their approved conversions and names the missing fact before anyone decides on a credit. - [Missing Conversions and Mixed Pack Sizes: Exceptions for Household Order Agents](https://www.stacksync.com/blog/missing-conversions-and-mixed-pack-sizes-exceptions-for-household-order-agents) When two mixed cases lack item-level contents or a pack factor is absent, the Genie holds the comparison and asks the right owner instead of picking a number that balances. [Explore all household consumables integration and automation guides ↗](https://www.stacksync.com/industry/cpg/household-consumables) ## Common evaluation questions ### Can the Genie choose a likely conversion to finish the case? No. A plausible conversion can produce a precise but wrong answer. Missing or conflicting factors require the responsible owner’s evidence. ### What does the Genie do when the distributor, invoice, and warehouse each use a different unit? It keeps all three. The distributor's case count from the Gmail claim, the multipack quantity on the NetSuite invoice, and the loose refill packages in the warehouse record each stay in their own unit, with the approved conversion and its effective version shown beside them. The Genie then states the supported difference, any alternative explanation, and which fact is missing. If the shipment was repacked, it asks for the approved contents record before calculating a shortage. Finance sees a comparison it can reproduce, not a verdict. ### Should we start with the Genie, or does something come before it? Two-way sync between NetSuite and Postgres comes first, so order lines, the sold-pack definition, and shipment evidence sit in one place an agent can cite. Workflows follow when damaged-return dispositions or wholesale replenishment approvals need routing to an owner with the result read back. Then configure this Genie to assemble the quantity claim from Gmail, the conversions, and the shipment facts into an investigation packet for finance. EDI comes last, carrying distributor purchase orders and case-level shipment evidence that later disputes are checked against.