Model decides skill use by default, but explicit contracts improve reliability
Rely on the model's default skill selection, or enforce deterministic contracts for production workflows.
The default behavior is the model decides when to use a skill. That’s often what you want. But when you’re running a production workflow with a clear contract (and you’d rather be deterministic than clever), just say: This is the simplest reliability lever you can pull. It turns fuzzy routing into an explicit contract.
While models can intelligently choose skills, for critical production workflows where predictability is paramount, explicitly instructing the model to use a specific skill or follow a defined contract ensures deterministic behavior over potentially 'clever' but unpredictable choices.
Instead of letting the model decide when to call the 'generate_report' skill, explicitly instruct it: 'Call the generate_report skill now with the following parameters...' for a deterministic outcome.
Agents can default to the model deciding when to use a skill. For production workflows requiring deterministic outcomes, explicitly instruct the model to use a specific skill or adhere to a defined contract, ensuring reliability over cleverness.
Explicitly defining skill invocation for production workflows removes ambiguity and ensures consistent, predictable behavior, which is crucial for reliability in automated processes.
- Shell + Skills + Compaction: Tips for long-running agents that do real work ↗OpenAI Developers Blog · OpenAI Developers Blog · Sep 3, 2026 · quoted as shared
First seen on Subvolts Sep 3, 2026. Updated Sep 11, 2026. Spotted a problem? Tell us.
- Shell + Skills + Compaction: Tips for long-running agents that do real workOpenAI · OpenAI Developers Blog · Sep 3, 2026
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- TemplateEvals CSV prompt list for agent skillsA CSV file template for listing prompts used in evaluating agent skills. · 20 min
- ChecklistAX Practitioner Playbook Evaluation Quality ChecklistReview your AI agent evaluation process before running it to ensure its quality and trustworthiness. · 30 min
- Skill or agent configJoplin agent for automated note filing and retrievalAutomate note organization and retrieval in Joplin using a custom agent and Python scripts. · 60 min
- HeuristicUse reasoning models for improved reliability on complex tasksEmploy reasoning models like o1, o3, and o4-mini for dramatically improved reliability on complex, multi-step work. · 5 min
- Setting tipStore AI agent traces and evaluation data with projectKeep traces, evaluation datasets, and results with your project for repeatable testing. · 5 min
- WorkflowBuild and test an AI agent using Microsoft Foundry ToolkitCreate, configure, test, and evaluate an AI agent within VS Code. · 60 min
Questions people ask
- Which AI tools does this work with?
- Any current model. It was seen with 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.