Who it is forA product team where prompt changes need a code deploy and nobody knows which version is live.
The problemPrompts hard-coded in the app are slow to change and impossible to compare.
The outcomeVersioned prompts fetched at runtime, with a playground for trying changes against real traces.
What you need first
- Docker and Docker Compose for local self-hosting, or a Langfuse Cloud account
- The Python or JS/TS SDK, or a supported framework integration
- For production: a VM, Kubernetes with Helm, or Terraform on AWS, Azure or GCP
Steps
- Run Langfuse self-hosted or on Langfuse Cloud
- Create your prompts in Prompt Management and fetch them from the SDK; caching on server and client keeps latency low
- When a trace shows a bad result, open it in the LLM Playground and try a prompt or model change
- Publish the better version and compare results over time
Prompt for your agent
Using langfuse/langfuse, move the prompts in <file> into Prompt Management, update my code to fetch them through the SDK, and set up the playground so I can test a new version against <example trace>.
Caveat. The README links to the docs for SDK code; the exact fetch call depends on your language.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for langfuse/langfuse and "Version and test prompts outside your code"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer