From 1fcb56c4c29e41747c733561879a65349bae15cd Mon Sep 17 00:00:00 2001 From: "mintlify[bot]" <109931778+mintlify[bot]@users.noreply.github.com> Date: Tue, 19 May 2026 08:22:06 +0000 Subject: [PATCH] docs: document AI agent suggestion chips --- guides/ai-agents/using-ai-agents.mdx | 33 ++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/guides/ai-agents/using-ai-agents.mdx b/guides/ai-agents/using-ai-agents.mdx index 525ad7a5..8303d296 100644 --- a/guides/ai-agents/using-ai-agents.mdx +++ b/guides/ai-agents/using-ai-agents.mdx @@ -20,6 +20,39 @@ As mentioned earlier, Lightdash agents use the **semantic layer** defined in you This ensures that the AI generates accurate queries and visualizations based on your specific data context. So, *when an Agent generates an answer, the output is a semantic query, **not SQL!*** This means that you can easily swap between the conversational AI interface and the standard Lightdash exploration experience. +## Suggestion chips + + + Suggestion chips are rolling out behind the **`ai-agent-suggestions`** feature flag. If you don't see them yet, ask your organization admin to enable the flag for your workspace. + + +Suggestion chips are short, clickable prompts that appear above the agent chat input. They give you a starting point so you don't have to begin every conversation from a blank box. Each chip is data-aware: it's generated against your project's explores, verified content, and your own recent threads, so the suggestions reflect what's actually in your semantic layer. + +### When chips appear + +- **Empty-state chips** show on a new, empty thread to help you kick off an analysis. +- **Continue chips** show after the agent replies and propose the most likely next step — a drill-down, a comparison, or a follow-up question grounded in the explore the agent just used. +- Chips fade out while you're scrolling back through long replies and reappear when you return to the input. + +### Chip types + +- **Prompt chips** send the chip's label to the agent as your next message. They map to one of the agent's tools (run a query, build a dashboard, find existing content, propose a semantic-layer change, or run SQL) and bias the agent toward that tool on the next turn. +- **Navigate chips** appear only on the empty state and only when you have recent threads worth resuming. Clicking one opens that thread in a new tab. Navigate chips are marked with an arrow icon and always point to a conversation you authored. + +### Using a chip + +Click a chip to either submit it as your next message (prompt chip) or jump to a recent thread (navigate chip). Prompt chips can be edited before sending — click the chip to drop the label into the input, then adjust the wording before pressing **Send**. + +### Configuring chips + +Suggestion chips have no per-agent setting today. They're generated automatically from: + +- The explores, dimensions, and metrics your agent has access to (controlled by [tags and data access](/guides/ai-agents/data-access)). +- Your project's [verified questions and verified content](/guides/ai-agents/verified-answers). +- Your own recent threads in the same project. + +To shape the chips you see, curate verified questions and verified content for the topics your team asks about most — those are the highest-quality signals the chip generator uses. + ## Asking about a chart or dashboard You can launch an AI conversation with a chart or dashboard pre-loaded as context. From the resource's `⋯` menu, click **Ask AI Agent**.