Autopilot

Autopilot is a scheduled agent that runs against a project on its own and keeps it healthy. Each run, it reviews recent activity, finds problems, fixes what it safely can, and flags the rest for review. Unlike conversational AI agents that respond to user questions, Autopilot is autonomous — it works in the background on a schedule you set.

​

What Autopilot does

Each run, Autopilot works through a fixed checklist: Every action is recorded in the activity log with a description of why Autopilot did it.

​

Action types

Each row in the activity log is tagged with one of:

• Auto-fixed — broken chart Autopilot fixed itself
• Cleaned up — content soft-deleted (admins can restore)
• Suggested — new chart drafted for review
• Flagged stale / broken / slow — recorded for review; future runs may escalate (e.g. soft-delete a stale flag that’s been ignored for 24h+)
• Insight — observation about popular content

​

Safety rules

Autopilot is conservative by default:

• Never touches content less than 30 days old
• Never soft-deletes a chart that’s the only chart on a dashboard
• Never modifies content it created itself (slugs prefixed agent-)
• Prefers flagging over deleting when in doubt
• Soft-delete only — admins can restore from the trash
• Reverses its own actions if it detects a mistake on the next run

​

Setup

Autopilot is configured per project from the project Home page. Schedule — choose how often it runs (every 6 hours, daily, etc.). Permissions — three capability toggles:

• Read content (always on) — reads project health signals, recent actions, and chart definitions
• Create content — drafts new chart suggestions in the “Agent Suggestions” space
• Modify existing content — soft-deletes stale content, fixes broken charts, reverses its own past actions

Disable both modify capabilities to run Autopilot in read-only mode (flags and insights only). Slack updates (optional) — post a summary of each run to a Slack channel. Requires the Slack integration.

​

AI provider and usage

Autopilot uses the organization’s default AI model. For the selected provider, it uses the organization’s key when configured, otherwise the instance key. Organization admins can manage keys and the default model in Settings → Ask AI → General. Autopilot has no per-project model override. Setup and the activity page show the current provider, model, and key source. Each new run records its selected model before execution, so historical runs keep their original attribution after settings change. Older runs without recorded model details show Model not recorded. Each scheduled run can make multiple model calls and consumes tokens on that key. More projects and more frequent schedules increase usage: for example, ten projects running daily schedule roughly 300 runs in a 30-day month, while running every six hours schedules roughly 1,200 runs. Manual runs add to this. Actual cost depends on the calls, token counts, model, caching, and your provider’s pricing agreement; the step limit is not a dollar spending limit. For usage reporting, Autopilot calls are tagged managed-agent, with the provider, model, project, and run ID. key_management distinguishes self-managed from lightdash-managed; an instance key can also be self-managed. Compare token usage with your provider’s billing records to reconcile charges. Missing provider usage and older run IDs remain unknown.

​

Reviewing activity

The Autopilot activity page shows every action across runs, with a sidebar that surfaces:

• Affected chart or dashboard context (space, last modified, views, verification status)
• Validation error details for broken content
• Execution time for slow queries
• Chart-as-code definition for suggested charts
• Autopilot’s reasoning for the action

Use the activity log to spot-check decisions, restore anything Autopilot got wrong, and accept or dismiss suggestions.