---
title: Roadmapping
description: "How Langfuse plans its roadmap: the quarterly process, who takes part, and how input from customers and the team turns into committed work."
---

# Roadmapping

## Why do we have a roadmapping process?

- Align on near-term product vision
- Resolve trade-offs between competing proposals
- Be intentional about where we are going
- Commit and be transparent about it with our community

## Process

  All process stages are run in the “Roadmap” Figjam (internal). We run this process once a quarter.

1. Exploration
   - Everyone gathers what they deem most important for the next quarter based on customer conversations, [GitHub Discussions](https://langfuse.com/ideas), and market insight.
   - Everyone is expected to cover this well for their own responsibilities/ownership, but contributions to everything else are welcome.
   - This is an individual process step, but it makes sense to discuss exploration results with colleagues that work on the same or related product areas before the exploration phase is over to refine the thoughts a bit.
2. Aggregation/drafting: Marc aggregates into a single holistic roadmap
3. Comments: everyone reviews draft and adds comments/questions
4. Discussion: teams meet to go through questions and agree on prioritization
5. Share
   - Update [langfuse.com/roadmap](https://langfuse.com/roadmap)
   - Organize community townhall and publish recording on YouTube ([playlist](https://www.youtube.com/playlist?list=PL4v4zZF1rGG6ICfvehJcDWAnAigSpEcxc))

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/handbook/product-engineering/how-we-work/roadmapping.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.