--- title: "Langfuse March Update" description: "Langfuse March Update: New UI, Prompt Composability, Environments & More!" ogImage: /images/blog/2025-03-31-langfuse-march-update/march-update.png tag: update date: 2025/03/31 author: "Marc" --- We've been busy this month at **Langfuse**! From a fresh UI redesign to major feature rollouts, here's a summary of the highlights: ## 💫 UI Redesign ![Langfuse UI Redesign](/images/blog/2025-03-31-langfuse-march-update/new-ui.gif) In the last few weeks, we've revamped the Trace and Prompt views. We love the new look as it makes the pages cleaner, simplifies navigation, includes more data, and speeds up navigation when going through a lot of data. → [Explore the new design](https://cloud.langfuse.com/) ## 🧩 Prompt Composability This was one of the most requested features: you can now reuse prompts in other prompts, letting you organize prompts in a modular way. For example, create a shared "guidelines" prompt and use it across all of your prompts. When guidelines are updated, all of your dependent prompts will be updated. → Check out the end-to-end demo [here](https://langfuse.com/changelog/2025-03-12-prompt-composability). ## 🗃️ Environments Langfuse is all about closing the loop between production and development to iterate quickly. That's why we introduced Environments, allowing you to separate environments (e.g. production, staging, dev) in Langfuse Tracing without needing to use tags or projects. This enables you to share prompts, datasets, and more within a project without mixing the source of your tracing data. → Learn how to set this up in our [docs](https://langfuse.com/docs/tracing-features/environments). ## ➕ More Features - **[OpenAI Responses API support in SDKs](https://langfuse.com/changelog/2025-03-17-openai-response-api-support)** Trace OpenAI Responses API calls with our Python and JS SDKs - **[Public API for Annotation Queues](https://langfuse.com/changelog/2025-03-13-public-api-annotation-queues)** Access and manage annotation queues programmatically with our new endpoints. - **[Langfuse Java Client](https://langfuse.com/changelog/2025-03-03-langfuse-java-client)** Langfuse offers a new Java API client for easy integration with Java applications. - **[Batch-export Scores via UI](https://langfuse.com/changelog/2025-03-13-batch-export-scores-ui)** Evaluation scores can now be exported in bulk as CSV or JSON directly from the Langfuse UI for easier one-off analysis and reporting. - **[Export via Blob Storage Integration](https://langfuse.com/docs/query-traces#blob-storage)** You can create scheduled exports to Blob Storage, e.g. S3, GCS, or Azure Blob Storage, for traces, observations, and scores. Thereby you can analyze and join the data in your own data warehouse. ## 🤝 New Integrations ![New Integrations](/images/blog/2025-03-31-langfuse-march-update/march-25-new-integrations.png) This month, we also added a couple of new integrations: - [OpenAI Agents SDK](https://langfuse.com/integrations/frameworks/openai-agents) - [Atla AI](https://docs.atla-ai.com/integration-langfuse) - [Databricks](https://www.linkedin.com/feed/update/urn:li:activity:7303456774387314688/) - [Fireworks AI](https://langfuse.com/integrations/model-providers/fireworks-ai) - [Quarkus LangChain4j](https://langfuse.com/integrations/frameworks/quarkus-langchain4j) - [Novita AI](https://langfuse.com/integrations/model-providers/novitaai) → If there is an integration you would like to see, add it to our [public roadmap on GitHub](https://github.com/orgs/langfuse/discussions/categories/ideas). ## 📅 Langfuse Town Hall (April 9th) Join us for our next Town Hall, where we will showcase live demos of the main Q1 releases and share a sneak peek at what's planned for Q2. → Sign up [here](https://lu.ma/6ba9aueo). ## 👨‍💻 We're Hiring in Berlin Langfuse is growing fast! We're looking for talented individuals to join our Berlin team. If you or someone you know might be interested, check out our open positions. We offer a USD 5K referral bonus! → [Learn more and apply](https://langfuse.com/careers) --- ## 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/blog/2025-03-31-langfuse-march-update.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**: , 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 `) to read or write traces, prompts, datasets, and scores from the terminal. Found an error in these docs? Please open an issue at .