--- title: "Langfuse April Update" description: "Japan Cloud Region, new Experiments, Langfuse Academy, LLM-as-a-Judge API and more" ogImage: /images/blog/2026-04-30-langfuse-april-update/japan-cloud.png tag: update date: 2026/04/30 author: "Marc" --- April shipped a lot. Japan Cloud went live, langfuse.com got a new design and brand, Langfuse Academy launched, and Experiments is now a top-level feature you can run from CI. ## Japan Cloud ![Japan Cloud](/images/blog/2026-04-30-langfuse-april-update/japan-cloud.png) Langfuse Cloud is now live in a dedicated Japan region, hosted in Tokyo (`ap-northeast-1`). Traces, prompts, and evaluation data stay in Japan. → Sign up at [jp.cloud.langfuse.com](https://jp.cloud.langfuse.com) ## Experiments ![Experiments](/images/blog/2026-04-30-langfuse-april-update/experiments.png) Experiments are now live alongside Datasets as their own top-level feature. You can run them with or without datasets, compare across runs, and track progress over time. Additionally, you can trigger experiments in CI with the new [Langfuse Experiments GitHub Action](/changelog/2026-05-25-experiment-ci-cd-gates). Gate PRs on regressions, post deltas as comments. → [Read the docs](/changelog/2026-04-13-experiments-rebuild) ## New Website ![New Website](/images/blog/2026-04-30-langfuse-april-update/new-website.png) [langfuse.com](https://langfuse.com) has a new design. Cleaner nav, faster pages, updated logo (the knot stays! 🪢). Let us know how you like it. ## Langfuse Academy ![Langfuse Academy](/images/blog/2026-04-30-langfuse-april-update/langfuse-academy.png) [Langfuse Academy](/academy) (beta) is live. It includes short lessons on tracing, evaluations, prompt management, and the patterns teams use in production. Onboard a teammate, or sharpen up on a specific concept. Langfuse is open source, and we want to open source the conceptual side of AI engineering too. The Academy is our way of making the core ideas, vocabulary, and workflows behind LLM application development easier to access for everyone. → [Academy](/academy) ## LLM-as-a-Judge API ![LLM-as-a-Judge API](/images/blog/2026-04-30-langfuse-april-update/llm-as-a-judge-api.png) The new [evaluators API](https://api.reference.langfuse.com/#tag/unstableevaluators) (unstable) lets you create, update, and version LLM-as-a-Judge evaluators in code. Hand it to a coding agent to set up evaluators across projects. Please note that this endpoint may evolve while the underlying evaluation data model is being redesigned. → [API Reference](https://api.reference.langfuse.com/#tag/unstableevaluators) ## Langfuse for agents If you missed these last time: - [Langfuse SKILL](/docs/api-and-data-platform/features/agent-skill) — Let code agents instrument your app and run evaluations. - [Langfuse CLI](/docs/api-and-data-platform/features/cli) — Query traces, manage prompts, run evals from the terminal. - [Langfuse MCP](/docs/api-and-data-platform/features/mcp-server) — Fetch and manage Langfuse prompts. ## Fixes & improvements - Feat: [5- and 20-minute blob storage export frequencies](https://github.com/langfuse/langfuse/pull/13126) - Feat: [Trigger evals from experiment runs](https://github.com/langfuse/langfuse/pull/13240) - Feat: [`DELETE` endpoint for LLM connections](https://github.com/langfuse/langfuse/pull/13247) - Feat: [`source=ANNOTATION` allowed on `POST /api/public/scores`](https://github.com/langfuse/langfuse/pull/13286) - Feat: [AWS Bedrock API Keys for LLM connections](https://github.com/langfuse/langfuse/pull/13098) - Feat: [OCI Object Storage native SDK integration](https://github.com/langfuse/langfuse/pull/12379) - Feat: [Time-window filtering for prompt metrics](https://github.com/langfuse/langfuse/pull/13282) - Feat: [Slack prompt notifications show change author](https://github.com/langfuse/langfuse/pull/13149) - Feat: ["None" filter mode for tags in trace sidebar](https://github.com/langfuse/langfuse/pull/13339) - Feat: [GPT-5.5](https://github.com/langfuse/langfuse/pull/13354) and [Claude Opus 4.7](https://github.com/langfuse/langfuse/pull/13214) model pricing - Fix: [Managed Ragas faithfulness evaluator scoring and prompt details](https://github.com/langfuse/langfuse/pull/13226) - Fix: [LLM-as-a-Judge queue stall](https://github.com/langfuse/langfuse/pull/13037) - Fix: [Crash on invalid JSONPath in dataset mapping editor](https://github.com/langfuse/langfuse/pull/13253) - Fix: [Constant-time comparison for admin API key auth](https://github.com/langfuse/langfuse/pull/13208) - and many more! ## Upcoming events - [ClickHouse Open House, SF](https://clickhouse.com/openhouse/san-francisco) — May 26–28, 2026, registrations open - [AWS Summit, Hamburg](https://aws.amazon.com/events/summits/hamburg/) — May 20, 2026 - [AI Engineer](https://webdirections.org/ai-engineer/speakers/muhammad-ali.php), Melbourne — June 3–4, 2026 - [AI Engineer World's Fair](https://www.ai.engineer/worldsfair), SF — June 29 – July 2, 2026 --- ## 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/2026-04-30-langfuse-april-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 .