{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicwolmu5wendwc5geh26cgqtzydtwisoknosj46ywcyjgv3hadh3u",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mi35mhp2znw2"
  },
  "path": "/t/having-issues-with-building-a-customer-support-ai-with-openai-need-help-to-deploy-production/1377925#post_4",
  "publishedAt": "2026-03-27T21:16:13.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@Abhishek_Kapoor",
    "Agent Builder",
    "ChatKit"
  ],
  "textContent": "Welcome to the developer community, @Abhishek_Kapoor.\n\nFor this kind of customer support AI workflow, I’d suggest trying Agent Builder. It’s a visual tool for building multi-step agent workflows, with templates, drag-and-drop nodes, typed inputs/outputs, and live previewing, so it’s a fast way to prototype and debug a support flow before moving to production.\n\nHere’s a template I found for a customer support agent:\n\n\nWhen you’re ready to deploy, you can publish the workflow as a versioned object and either plug it into your app with ChatKit or export the code and use the Agents SDK for a more custom setup.",
  "title": "Having issues with building a customer support AI with OpenAI . Need help to deploy production?"
}