--- title: "Langfuse March Update" description: "Agent Skill, Langfuse CLI, boolean and categorical LLM-as-a-Judge scores, Kiro integration, and more" ogImage: /images/blog/2026-03-31-langfuse-march-update/agent-skill.png tag: update date: 2026/03/31 author: "Marc" --- The past months we have been shipping a lot to make Langfuse much easier to use for your coding agents. If you are not using Langfuse through your coding agent yet, we strongly recommend giving it a spin! ## Agent Skill ![Agent Skill](/images/blog/2026-03-31-langfuse-march-update/agent-skill.png) The [Langfuse Agent Skill](/docs/api-and-data-platform/features/agent-skill) helps coding agents to use Langfuse effectively. It follows the open [Agent Skills](https://github.com/anthropics/skills) standard and works with Claude Code, Cursor, Codex, and others. Install it in one line: ``` npx skills add langfuse/skills --skill "langfuse" ``` Or just ask your coding agent to install it from `github.com/langfuse/skills`. Once installed, your agent can query traces, create datasets, update prompts, migrate hardcoded prompts to Langfuse Prompt Management, and set up observability — all without leaving your editor. Even if you are already successfully using Langfuse, the Skill can help you improve your workflows and instrumentation. ## Langfuse CLI ![Langfuse CLI](/images/blog/2026-03-31-langfuse-march-update/langfuse-cli.png) The skill uses the [Langfuse CLI](/docs/api-and-data-platform/features/cli) under the hood. It wraps the entire Langfuse API, auto-generated from our OpenAPI spec so it's always in sync. Every endpoint becomes a CLI command: traces, prompts, datasets, scores, sessions, metrics, and more. Built for agents, but useful for humans too. Script your workflows, automate batch-scoring, or sync prompts across environments in CI/CD. → [npm](https://www.npmjs.com/package/langfuse-cli) ## Further reading Here are some pointers for what to do with the Skill and CLI: - **Getting started with all Langfuse features.** Using the Skill it is incredibly easy to get started using more of the Langfuse platform. Just ask your agent that you would like to test a certain feature and it can propose useful first use cases and start implementing them. - **Automatic prompt improvement.** Annotate a few traces in Langfuse, then let an agent fetch your feedback, analyze patterns, and propose prompt changes. A fast loop from rough to robust. → [Read the guide](/blog/2026-02-16-prompt-improvement-claude-skills) We have also learned a lot about building efficient Skills: - **Evaluating skill quality.** We used Langfuse datasets, tracing, and the Claude Agent SDK to systematically test and improve the Skill itself. Small details matter: a single comment saying "optional" instead of "mandatory" caused consistent agent failures. → [Blog post](/blog/2026-02-26-evaluate-ai-agent-skills) - **Optimizing skills with Autoresearch.** We ran Karpathy's autoresearch on our prompt migration skill. Score went from 0.35 to 0.82. Not all changes were keepers, but the process surfaced failure modes we'd never have found manually. → [Blog post](/blog/2026-03-24-optimizing-ai-skill-with-autoresearch) ## Fixes & improvements - Feat: [Boolean Scores in LLM-as-a-Judge](/changelog/2026-04-08-boolean-llm-as-a-judge-scores) - Feat: [Categorical Scores in LLM-as-a-Judge](/changelog/2026-03-20-categorical-llm-as-a-judge-scores) - Feat: [Delete entire prompt folders](https://github.com/langfuse/langfuse/pull/11920) - Feat: [Add to dataset batch action from events table](https://github.com/langfuse/langfuse/pull/12144) - Feat: [Show evaluation prompt on hover in evals](https://github.com/langfuse/langfuse/pull/12208) - Feat: [Support Japanese characters in prompt variables](https://github.com/langfuse/langfuse/pull/11509) - Feat: [Position in trace filter](https://github.com/langfuse/langfuse/pull/12058) - UI: [Chart loading and failure hints](https://github.com/langfuse/langfuse/pull/12180) - UI: [Tooltip support for filter facets](https://github.com/langfuse/langfuse/pull/12168) - UX: [Prevent focus loss when typing unit name in price editor](https://github.com/langfuse/langfuse/pull/12344) - UX: [Mutual exclusion between temperature and top_p for Anthropic models](https://github.com/langfuse/langfuse/pull/12020) - UX: [Data shown in JSON beta viewer for sessions](https://github.com/langfuse/langfuse/pull/12343) - API: [Performance controls for `GET /api/public/traces`](https://github.com/langfuse/langfuse/pull/12062) - API: [Typed `ObservationsV2Response` data field](https://github.com/langfuse/langfuse/pull/12287) - Fix: [Usage/details summing now computes correctly](https://github.com/langfuse/langfuse/pull/12130) - Integration: [Kiro](/integrations/developer-tools/kiro) — AI-powered IDE by AWS - and many more! ## Upcoming events - [AI Engineer Europe](https://www.ai.engineer/europe), London — April 8, 2026 - [AI Demo Night in SF](https://luma.com/jyzlu78v) — April 9, 2026 - Co-hosting a [Hackathon with OpenAI in Berlin](https://luma.com/m7263aao) — April 15, 2026 - [Google Cloud Next in Vegas](https://www.googlecloudevents.com/next-vegas) — April 22–24, 2026 - [Clickhouse Openhouse in SF](https://clickhouse.com/openhouse/san-francisco) — May 26–28, 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/2026-03-31-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 .