--- title: "AI agents for equipment aftermarket parts requests" description: "Use a Genie to assemble the machine history, approved part references and commercial context behind an aftermarket request." canonical: https://www.stacksync.com/use-case/equipment-ai-aftermarket-parts-requests last_modified: 2026-09-21 --- Industrial equipment and machinery # AI agents for equipment aftermarket parts requests > 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 ![Industrial equipment and machinery systems connected through Stacksync two-way sync: Salesforce, NetSuite, Acumatica, PostgreSQL](https://www.stacksync.com/images/industry-heroes/icp-industrial-equipment-machinery-800.webp) Use a Genie to assemble the machine history, approved part references and commercial context behind an aftermarket request. Stacksync fits equipment builders whose service teams spend time searching several systems before they can prepare a compatible parts proposal. The Genie prepares evidence; service engineering and commercial owners approve the consequential decisions. A customer sends a photo or asset label, and the team must reconstruct the installed configuration before it can responsibly recommend a replacement. [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 COOs, service directors and IT leaders at US equipment builders with 100–1,000 employees and a mix of manufacturing, distribution and service. ### Resolve the installed context Gather serial, shipment and approved modification evidence while preserving uncertain identity matches. ### Prepare supported part proposals Show the applicable replacement or kit rule and required companion components. ### Keep commercial decisions explicit Warranty, pricing and delivery acceptance remain separately owned; unresolved questions do not disappear inside a generated answer. The process, end to end ## Follow the work across systems an aftermarket leader wants a reviewer to receive one packet containing the resolved serial, retrofit history, supported replacement and open questions. Evaluate a transferred machine and a conditional supersession rather than only a simple catalog lookup. [Salesforce connector](https://www.stacksync.com/connectors/salesforce) [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 - Approved serial and installed-configuration records. - Reviewed replacement, supersession and kit references. - A service reviewer and the intended quote or order handoff. 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 equipment aftermarket requests: prepare compatible parts proposals](https://www.stacksync.com/blog/equipment-genie-aftermarket-part-request-guide) From a customer photo and asset label, the Genie prepares a review packet with the resolved serial, supported replacement, stock context and the questions still open. - [Equipment parts AI exceptions: serial ambiguity, supersession and incomplete kits](https://www.stacksync.com/blog/equipment-genie-part-supersession-serial-exceptions) A plausible active SKU is not a compatible part; these exceptions show which serial, retrofit or kit fact is missing before service engineering can sign off. [Explore all industrial equipment and machinery integration and automation guides ↗](https://www.stacksync.com/industry/manufacturing/industrial-equipment-machinery) ## Common evaluation questions ### Can it identify parts from an image? Images can assist investigation, but the accepted proposal should follow the manufacturer’s identification and compatibility process. ### How does the Genie handle a machine it cannot identify? It keeps the candidates open instead of picking one. When a photo or local asset label matches more than one serial, or the retrofit history is incomplete, the packet lists each candidate, the evidence that separates them and the specific nameplate or shipment reference that would settle it. The service reviewer decides whether to ask the customer or accept a match. No replacement is proposed as compatible until the installed configuration is established. ### How should savings be calculated? Measure reviewer search and clarification effort, proposal corrections and completed accepted handoffs, including the cost of reviewing Genie output. ### Where do Genies sit in the product order for aftermarket parts requests? Two-way sync goes in first, so Salesforce, NetSuite and Postgres agree on the serial and installed configuration behind the resolved machine, part proposal and commercial draft. Workflows come next when a warranty replacement handoff needs coverage and compatibility matched with named owners. Then the Genie reads those records, assembles the evidence into a review packet and prepares the next action, while service engineering approves the part and commercial owners approve price and coverage. EDI is a separate transport for distributor purchase orders with kits and partial shipments.