Sharing all state information between UI, model, and server
Avoid sharing all state everywhere; intentionally limit visibility to what each component needs.
Explicitly decide and define which information needs to be shared, when it should be shared, and who needs visibility into it. Use different tool output fields to manage this, like passing specific data to a widget's _meta field.
Sharing all state information between the UI, the model, and the server in a ChatGPT app.
Different parts of a ChatGPT app often require intentionally different views of the same state. Sharing everything can lead to confusion and inefficiency, whereas selective sharing improves clarity and functionality.
Avoid the mistake of sharing all state information between the UI, model, and server in ChatGPT apps. Instead, intentionally decide and define what information is shared, when, and with whom, using specific tool output fields for targeted data exchange.
- 15 lessons learned building ChatGPT Apps ↗OpenAI Developers Blog · OpenAI Developers Blog · Sep 3, 2026 · paraphrased
First seen on Subvolts Sep 3, 2026. Updated Sep 11, 2026. Spotted a problem? Tell us.
- 15 lessons learned building ChatGPT AppsOpenAI · OpenAI Developers Blog · Sep 3, 2026
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- HeuristicDefine task completion clearly to avoid premature stoppingExplicitly define what 'done' means for a task to ensure AI models complete the full scope. · 10 min
- Anti-patternBuilding agent infrastructure from scratchAvoid piecing together agent infrastructure; use standardized SDKs and native sandbox support. · 5 min
- Setting tipAgent workspace portability with Manifest abstractionUse the Manifest abstraction to describe agent workspaces for portability across different providers. · 10 min
- ToolOpenAI Agents SDK for building agentsSDK for building agents that can inspect files, run commands, edit code, and work on long-horizon tasks. · 15 min
- Anti-patternOverly specific instructions for advanced AI modelsAvoid detailed itineraries; newer models handle nuance and ambiguity better. · 10 min
- Anti-patternPrompting AI to read all project docs before every editAvoid forcing AI to read extensive documentation before simple edits; use contextual pointers instead. · 10 min
Questions people ask
- Which AI tools does this work with?
- The sources used it with ChatGPT.
- Where did this come from?
- OpenAI Developers Blog (OpenAI Developers Blog). Subvolts collected, normalized and credited it; the link above opens the original.