Define task completion clearly to avoid premature stopping
Explicitly define what 'done' means for a task to ensure AI models complete the full scope.
A requirement to stop for review after the first implementation will pull the model toward an earlier stopping point, so check whether that’s a decision you actually need to make.
Newer models might be more tentative and seek review after an initial implementation. Clearly defining the full scope of work, including testing and refinement, ensures the model continues until the task is truly complete.
Instead of 'Implement the feature', use 'Implement the feature, run tests, fix failures, and ensure the implementation is running locally.'
Clearly define the full scope of a task, including all necessary steps like implementation, testing, and refinement. This prevents AI models from stopping prematurely and ensures they complete the entire objective.
- Rethinking skills and prompts for GPT-6 Astra ↗OpenAI Developers Blog · OpenAI Developers Blog · Sep 12, 2026 · paraphrased
First seen on Subvolts Sep 12, 2026. Updated Sep 12, 2026. Spotted a problem? Tell us.
- Rethinking skills and prompts for GPT-6 AstraOpenAI · OpenAI Developers Blog · Sep 12, 2026
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- 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
- HeuristicSimplify instructions for newer, more capable AI modelsAvoid overly specific instructions; newer models understand nuance and ambiguity better. · 10 min
Questions people ask
- Which AI tools does this work with?
- Any current model. It was seen with ChatGPT in the sources.
- Where did this come from?
- OpenAI Developers Blog (OpenAI Developers Blog). Subvolts collected, normalized and credited it; the link above opens the original.