{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreige7gcuryb2lldjgwhhj6dw5eb3iw6vno72rrhg7dijom2xhvyqya",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mhzvcfhx5yq2"
  },
  "path": "/t/having-issues-with-building-a-customer-support-ai-with-openai-need-help-to-deploy-production/1377925#post_1",
  "publishedAt": "2026-03-27T09:23:11.000Z",
  "site": "https://community.openai.com",
  "textContent": "Hi everyone,\n\nI am trying to build a customer support AI for our organization using OpenAI, and honestly, the experience has been more frustrating than expected.\n\nEarlier, I used the Assistants API for document indexing and retrieval, which was working decently. The issues with that were the lack of agentic behavior and reliability. Later, I moved toward the Responses API file search and also started experimenting with the Agents SDK.\n\nBut it still is not working well for us.\n\nI want a customer service AI that can answer from our documents, support customers reliably without hallucinations, follow instructions consistently, perform actions, and give grounded responses that are actually useful.\n\nI am stitching together multiple pieces, and even after doing that, the system does not behave the way I expect in real-world use. The models I have tested are GPT-5.2, GPT-5 mini, o3-mini, and GPT-4 Turbo previously.\n\nThe main issue is:\n\n  * retrieval does not feel dependable, responses are inconsistent, behavior is unpredictable, and the overall setup still does not feel solid enough for production customer support\n\n\n\nAt this point, I am tired of piecing everything together and still not getting the quality we need.\n\nSo I wanted to ask people here who have actually made this work in production: has anyone built a genuinely reliable customer support AI that does not hallucinate with the current OpenAI stack? Are you using the Agents SDK directly, or mostly building your own orchestration? For document-based support, what are you using? And how are you handling the model variations, like when the model sometimes answers the same query correctly and sometimes gets it wrong?\n\nI want something dependable enough for real organizational customer service. I am fed up with building this way; I have already spent a lot of time and resources on this project.\n\nI would really appreciate honest advice or any alternative approach from anyone who has gone through this. I no longer want to keep stretching things my team members are asking questions. Thanks.",
  "title": "Having issues with building a customer support AI with OpenAI . Need help to deploy production?"
}