Skip to content

Cross-link recurring deliveries from AI agent conversations #937

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mintlify wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Cross-link recurring deliveries from AI agent conversations #937

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions guides/ai-agents.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,7 @@ This guide covers everything you need to know about AI agents in Lightdash:
- **AI Router** - Automatically send each question to the best-fit agent, so users don't have to pick one first
- **Automatic visualizations** - Get charts, tables, and dashboards generated based on your questions
- **Slack integration** - Collaborate with your team directly in Slack channels
- **[Recurring deliveries from a conversation](/guides/ai-agents/using-ai-agents#schedule-a-recurring-delivery-from-a-conversation)** - Turn an agent conversation into a [scheduled delivery](/guides/how-to-create-scheduled-deliveries) that re-runs the agent on your chosen frequency and sends the refreshed chart plus an AI-written summary to Slack, email, or Microsoft Teams
- **Memory and learning** - Agents remember corrections and improve over time
- **[Reviews (Beta)](/guides/ai-agents/reviews)** - Lightdash scans agent turns for likely-wrong answers and proposes one-click fixes to your semantic layer or [project context](/guides/ai-agents/reviews#the-lightdashproject_contextyml-file), so admins can improve agents at the source
- **Knowledge documents** - Upload glossaries, metric definitions, and business context for your agent to consult
Expand Down
4 changes: 4 additions & 0 deletions guides/how-to-create-scheduled-deliveries.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,10 @@ Note that the interactive viewer role can only create and edit their _own_ sched

</Info>

<Tip>
**Starting from an AI agent conversation?** You can [schedule a recurring delivery directly from an agent conversation](/guides/ai-agents/using-ai-agents#schedule-a-recurring-delivery-from-a-conversation) — Lightdash re-runs the agent on your chosen frequency and sends the refreshed chart, plus an AI-written summary, to Slack, email, or Microsoft Teams. The form opens pre-filled from the conversation, so you get the same style of answer on a schedule without rebuilding anything.
</Tip>

To create a scheduled delivery, click on the three-dot menu in the top-right corner of your chart or dashboard, then click on `scheduled deliveries`.

<Frame>
Expand Down
Loading