platform-guideline 4 linked patterns checked
OpenAI Web search guide
States that responses using web search include inline citations and url_citation annotations, and that citations shown to users should be visible and clickable.
Read with a purpose
What this source can teach
Use this source to understand a platform convention and the setting it was designed for.
- Start with the original. Open the source and find the guidance or example relevant to your task.
- Trace the connection. Use the claim notes below to see how this site applies the source to specific patterns.
- Check the setting. Compare the source's platform, people, and constraints with your own decision.
Pattern Decisions This Source Supports
| Pattern | Supported decision | Required contract | Claim note |
|---|---|---|---|
| AI answer without sources | Flag this anti-pattern when an AI answer makes evidence-dependent claims and provides no source link, citation marker, grounding panel, source scope, or verification action. | Evidence-dependent answers must expose whether sources were searched, retrieved, used, unavailable, permission-limited, failed, or not required. | Supports visible source references for web-search-backed answers. |
| Citation display | Choose citation display when the main user need is verifying a generated or summarized claim against the source that supports it. | Each citation marker opens or focuses the source record that supports the adjacent claim. | Supports visible, clickable inline citations for web-search output. |
| Source grounding display | Choose source grounding display when users need answer-wide evidence coverage, source scope, retrieved-versus-used source status, or unsupported-claim visibility. | The grounding display names the source scope that was available for this answer, not just sources the user might expect. | Supports web-search citations and visible source references. |
| Tool-use visibility | Choose tool-use visibility when users need to inspect exact tool names, purposes, inputs, outputs, permissions, side effects, failures, or redactions. | Each tool-use item identifies one tool call or tool-call attempt with stable call ID, run ID, step ID, tool name, status, timestamp, and permission scope. | Supports web-search tool outputs and citation annotations that may need source-aware inspection. |
Comparisons supported by this source
- AI answer without sources vs source grounding display vs citation display vs confidence / uncertainty display vs streaming response vs correction feedback
Supports visible source references for web-search-backed output.
- Citation display vs chat interface vs streaming response vs related links vs tooltip
Supports visible and clickable inline citations for web-search results.
- Source grounding display vs citation display vs chat interface vs streaming response vs related links
Supports visible inline citations for web-search-backed output.
- Tool-use visibility vs agent progress trace vs source grounding display vs citation display vs activity log vs human approval gate
Supports distinguishing web-search tool output inspection from claim-level citation mapping.
Evidence Role
This source is treated as platform-guideline evidence. Its value comes from the specific claims and setting described above.
Publisher: OpenAI. Last checked: .