--- date: 2026-05-14 title: "Introducing Langfuse Academy" description: "Langfuse Academy is our open explanation of the AI engineering lifecycle: tracing, monitoring, datasets, experiments, and evaluation, and how the pieces fit together." author: Lotte, Annabell ogImage: /images/changelog/2026-05-14-langfuse-academy.png --- > **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com). Today we're launching the [Langfuse Academy](https://langfuse.com/academy), a free, open resource that explains the AI engineering lifecycle and how the parts connect. ## Why we built it This is a new field, and users have often asked where they should start. Common practices have emerged over the past years, but the vocabulary and workflows are spread across blog posts, product docs, and teams internally. The Academy is our attempt to put them in one place. The tooling only helps if the underlying ideas are clear. Teams move faster when AI engineers, product managers, and leadership share the same vocabulary for tracing, evaluation, datasets, and experiments. ## Who is this for The Academy is written to be useful for AI engineers and software engineers building LLM applications, for PMs reasoning about quality and tradeoffs, for technical and business leaders who want a working understanding of how AI systems are improved, and for AI agents that support humans in doing this work. ## What's in the Academy today The Academy follows the [AI engineering loop](https://langfuse.com/academy/ai-engineering-loop) from first visibility into production behavior through to structured improvement: - [Trace](https://langfuse.com/academy/tracing) - [Monitor](https://langfuse.com/academy/monitoring) - [Build datasets](https://langfuse.com/academy/datasets) - [Experiment](https://langfuse.com/academy/experiments) - [Evaluate](https://langfuse.com/academy/evaluate) Each page explains why a step exists, what problem it solves, and how it connects to the next one. You can read the full sequence or jump to the topic that is most relevant to your team right now. ## What's next We plan to keep expanding the Academy with deeper dives on individual topics, more examples, and guides to put this into practice. Over time we want it to be the resource we wish had existed when we started building Langfuse. ## Try it out and tell us what you think You can find the Academy at [langfuse.com/academy](https://langfuse.com/academy). We're just getting started here and are very curious to hear what you think. If something is unclear, if a topic is missing, or if you'd approach a step differently, we'd love for you to open an issue on [GitHub](https://github.com/langfuse/langfuse-docs/issues). Your feedback will directly shape what we publish next. --- ## 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/changelog/2026-05-14-langfuse-academy.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 .