Ensure apps clearly move the needle on know, do, or show
Apps must demonstrably improve user understanding, actionability, or visualization.
An app must clearly move the needle on at least one of 'know,' 'do,' or 'show' to add value.
If an app doesn't demonstrably help users know something new, do something they couldn't before, or see information in a more useful way, it risks feeling like it's not adding value beyond the base ChatGPT capabilities. This applies to both productivity and entertainment apps.
A real estate app that shows live property listings (know/show) and allows filtering (do) clearly adds value beyond the base model.
Verify that your ChatGPT app enhances user experience by providing new knowledge, enabling new actions, or presenting information more effectively. If it doesn't improve on 'know,' 'do,' or 'show,' it may not be adding sufficient value.
This principle ensures that the app's integration into ChatGPT provides tangible benefits. By focusing on these three core areas of improvement, developers can ensure their apps offer a distinct advantage over the base model's capabilities.
This heuristic may be less critical for purely experimental or novelty apps where the primary value is novelty itself.
- What makes a great ChatGPT app ↗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.
- What makes a great ChatGPT appOpenAI · 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
- HeuristicShorten skill descriptions for better model context managementKeep skill descriptions brief and clear to help models pick the right skill and avoid context overload. · 15 min
- HeuristicUse progressive disclosure for complex skills with multiple workflowsFor skills with many workflows, use a minimal root document that links to supporting details. · 20 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
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.