Overview
How might we design contextual ai suggestions so people can trust and act on AI output?
When this pattern fits
- Ideal for complex applications, design tools, and productivity platforms where contextual AI suggestions improve feature discovery and workflow efficiency.
When to skip or lighten it
- Context too ambiguous to suggest safely.
- Suggestions on every keystroke causing jitter.
- Actions that need explicit user data consent first.
States
State model coming soon
Key UX elements
Key UX elements coming soon
Anti-patterns to avoid
Same three suggestions regardless of selection.
Suggestion chip covering the text being edited.
No keyboard path to accept or ignore.
Running expensive AI on every hover.
How products use it
| Product | Implementation |
|---|---|
| Figma | AI actions on selected frames and text layers. |
| Cursor | Composer suggestions based on open files and selection. |
| Notion | Ask AI on highlighted blocks and databases. |
| Linear | Issue summarize and triage prompts in context. |
Implementation
Copy this prompt to generate a production-ready implementation in Cursor, Claude Code, Lovable, or any AI coding agent.
Generate a production-ready implementation of the "Contextual AI Suggestions" AI interface design pattern.
Pattern Definition:Frequently asked questions
How pick which actions to show?
Map selection type and app surface to a small ranked list, max three visible.
Contextual suggestions vs nudge?
Suggestions are actionable AI tasks. Nudges are lighter educational hints.
Latency?
Show chips instantly from rules; defer heavy ranking if needed.
Dismiss memory?
Do not resurface dismissed actions for that context in the session.