openai · OpenAI Platform Docs
Agents Results and state
Explains how to handle agent outputs by selecting appropriate result surfaces for user answers, session management, handoffs, and managing interrupted runs via state snapshots.
Derived skill
Files assembled from official documentation
Viewing SKILL.md
Agents Results and state
Explains how to handle agent outputs by selecting appropriate result surfaces for user answers, session management, handoffs, and managing interrupted runs via state snapshots.
When To Use
Use when you need to implement agent continuation strategies, manage handoffs between specialists, or handle interrupted runs that require human approval via state serialization.
Reference Files
| File | Contains | Use For |
|---|---|---|
SKILL.md | Entry point: scope, routing table, and workflow. | Start here. |
docs/agents-results-and-state-workflow-guide.md | A guide explaining the different result surfaces, state management, and interruption handling when running OpenAI agents. | Questions about a guide explaining the different result surfaces, state management, and interruption handling when running OpenAI age... |
What This Skill Covers
- When you run an agent, the result is more than just the final answer. It's also the handoff boundary, the next-turn continuation surface, and the resumable s...
- Main sections:
Choose the result surface you need,What to carry into the next turn,Interrupted runs return state, not a final answer,Richer item and diagnostics surfaces,Next steps.
Workflow
- Open the most relevant file under
docs/for the exact documented workflow and wording. - Open
schemas/files for exact structured contracts. - Open
examples/files for concrete requests, commands, snippets, and manifests. - Do not add behavior or configuration that is not present in the attached source files.
Canonical source: https://developers.openai.com/api/docs/guides/agents/results.md
