Langfuse Assistant
The Langfuse Assistant is an in-product assistant for exploring your Langfuse project data. Ask questions about traces, observations, sessions, metrics, and Langfuse workflows in plain language.
The Langfuse Assistant is currently in beta and only available on Langfuse Cloud.
What you can ask
Ask the Assistant questions such as:
- "Which traces had the highest latency yesterday?"
- "Show me failed generations in the last hour."
- "What's my token spend this week, broken down by model?"
- "How do I set up an evaluator?"
- "Open the traces table filtered to errors from today."
How it works
The Assistant uses the Langfuse MCP server and additional tools to answer questions, inspect project data, and propose navigation actions.
The Assistant can:
- Query traces, observations, sessions, and metrics through Langfuse tools
- Search Langfuse documentation
- Propose links to Langfuse pages such as traces, sessions, dashboards, prompts, datasets, experiments, evals, monitors, and project settings
The Assistant does not automatically navigate or modify project data. When a destination is useful, it proposes an action that you confirm.
The Assistant is also aware of your current context in the Langfuse UI, such as the current trace, observation, session, or dashboard, as well as user metadata such as your name, browser language, and timezone. This context is used to provide more relevant answers and propose actions.
Access and availability
It is currently available on Langfuse Cloud and not yet available for self-hosted deployments.
Data privacy and security
The Assistant follows the same data handling model as other Langfuse AI features. See AI Features for the canonical security and privacy details.
Key points:
- Model requests are handled in the same AWS region as your Langfuse data region.
- Assistant access is scoped to the authenticated user and current project.
- AI feature tracing for product and service improvement can be enabled or disabled separately by organization admins and owners.
Conversation history
Assistant conversations are saved per user and project so you can return to previous conversations.
Feedback
You can submit thumbs-up or thumbs-down feedback on Assistant responses. If AI feature tracing is enabled, feedback may be used for product and service improvement.
You can also share your thoughts in our feedback discussion.
Limitations
The Assistant is a beta feature. It may misunderstand a question or return incomplete results. Verify important answers before acting on them.
Related resources
Last edited
