{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicoxnipqazjajgkv5kaweavww4fdn3phdwnp747vznk2kgmstjkhe",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mgerg3hfic32"
  },
  "path": "/t/chatgpt-apps-embedded-ui-no-longer-renders-on-web-after-agentic-multi-step-exploration/1375844#post_1",
  "publishedAt": "2026-03-06T04:49:20.000Z",
  "site": "https://community.openai.com",
  "textContent": "We’re building a ChatGPT App that lets users explore and view our own content.\n\nUntil a few days ago, a workflow like this worked on web:\n\n  1. GPT performs agentic multi-step exploration\n\n  2. It chains multiple data-only calls to resolve candidates/details\n\n  3. It then invokes a UI-rendering step to surface the result in chat\n\n\n\n\nNow, the exploration/data steps still succeed, and the UI-rendering call also appears to be invoked, but the embedded UI never actually appears in the web client.\n\nThe key pattern is:\n\n  * data-only exploration succeeds\n\n  * standalone UI rendering works\n\n  * UI rendering after sequential exploration calls no longer surfaces on web\n\n\n\n\nSo this does not look like a retrieval failure. It looks more like a regression in the handoff from multi-step exploration to embedded UI surfacing.\n\nAlso worth noting:\n\n  * Web: embedded UI does not appear\n\n  * Mac desktop: still behaves as expected\n\n\n\n\nHas anyone else seen a recent change in ChatGPT Apps where the UI-rendering step is invoked but the embedded UI does not render after agentic multi-step exploration, specifically on web?",
  "title": "ChatGPT Apps: Embedded UI no longer renders on web after agentic multi-step exploration"
}