> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lightdash.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AI thread debug dump

> Enable and safely use the AI agent thread debug dump on a self-hosted Lightdash instance.

<Note>
  🛠 This page is for engineering teams self-hosting their own Lightdash instance.
</Note>

<Warning>
  🔑 **Enterprise feature** — the AI thread debug dump requires a valid [Enterprise License Key](/self-host/customize-deployment/enterprise-license-keys) and only works when [AI Analyst](/self-host/customize-deployment/environment-variables#ai-analyst) is configured.
</Warning>

## What it is

Organization AI admins can download a sanitized JSON dump of any AI agent thread to share with Lightdash support when troubleshooting agent behaviour, without exposing customer data by default.

## Prerequisites

* A self-hosted Lightdash instance with a valid `LIGHTDASH_LICENSE_KEY`.
* [AI Analyst enabled](/self-host/customize-deployment/environment-variables#ai-analyst) (`AI_COPILOT_ENABLED=true` and a configured provider).
* The thread debug dump feature enabled by setting [`AI_COPILOT_THREAD_DUMP_ENABLED=true`](/self-host/customize-deployment/environment-variables#ai-analyst) on your Lightdash deployment. It is disabled by default.

## Who can download a dump

Only organization-level AI admins can download thread dumps. Concretely, the user must have `manage` permission on the organization's AI agents. Project-scoped agent managers cannot download dumps, even for threads inside a project they manage.

Eligible admins download a dump from **Settings → Ask AI → Threads**, using the per-row download action next to each thread.

For a refresher on the underlying roles, see [Workspace roles](/references/workspace/roles).

## What the dump contains

Each dump is a single JSON file that includes:

* **The full conversation** — every user prompt, agent response, and tool call, including tool arguments.
* **Agent configuration as of download time** — the agent's instructions, model, and feature toggles.
* **The Lightdash version** the instance was running at download time.
* **UUIDs only** — no user names or email addresses are included.
* **Chart and dashboard artifact configs** produced by the agent during the conversation.

## Accepted risks

The dump is a support-oriented artifact, not a fully anonymized export. Before enabling the feature or sharing a file, make sure your team understands the following:

<Warning>
  Lightdash redacts query result rows, field value searches, and any documents or repo contents the agent read. Agent responses are **not** redacted, so data values quoted in an answer still appear verbatim. Review the file before sharing it.
</Warning>

* **Downloaded files leave Lightdash's retention window.** Once a dump is on disk, Lightdash cannot delete or expire it. The customer owns its lifecycle from that point on.
* **End users are not notified** that their agent conversations may be shared. Organizations with internal privacy-notice obligations (for example, EU works councils) should document this internally before enabling the feature.
* **The agent configuration block is a point-in-time snapshot.** It reflects the agent's settings at the moment of download, not at the time of the conversation. If instructions, model, or toggles changed after the thread ran, the block shows the current values. Per-turn model configuration is historical, so the specific model used for each response in the conversation is preserved even if the agent's default model has since changed.

## Related

* [AI Analyst environment variables](/self-host/customize-deployment/environment-variables#ai-analyst)
* [Lightdash AI agents overview](/guides/ai-agents)