Agentic Prompt Management
AI agents can work with your Langfuse prompt library while they edit application code. There are different ways for agents to access your data:
Choose an access method
| Agent capabilities | Recommended access |
|---|---|
| Can install tools and run shell commands | Install the Langfuse Agent Skill. It teaches the agent Langfuse workflows and uses the Langfuse CLI to query and update project data. |
| Cannot install tools or run shell commands | Connect the Langfuse MCP server to expose Langfuse operations as tools. |
| Runs as part of a script or CI/CD pipeline | Use the Langfuse CLI directly or call the Public API. |
Example workflows
Ask your agent to:
- Migrate hardcoded prompts from a codebase to Langfuse
- Retrieve a prompt and compare its latest versions
- Create a new text or chat prompt version
- Promote a tested prompt version by updating its deployment labels
Work across Langfuse
Agents can also investigate production behavior and run evaluation workflows in Langfuse.
Related guides and blog posts
- Automatically improve prompts with Agent Skills: Use the Langfuse skill to analyze trace feedback and iteratively improve your prompts.
- Headless Langfuse from your coding agent: Instrument an application, analyze traces, build a dataset, and run evaluations without leaving your coding agent.