--- title: Customers description: Learn how customers build, evaluate, and improve AI applications with Langfuse. showInCustomerIndex: false --- # Customer stories ## Canva > "Langfuse hits the sweet spot between engineering requirements and empowerment of non-technical users to contribute their domain expertise." > > — Andreas Schuster, Head of Product, AI Help Experience [Read the story](/users/canva) ## Khan Academy > "Langfuse has enabled our developers to get extremely fast feedback. It's fundamental to how our developers understand their AI implementations." > > — Walt Wells, Staff Software Engineer [Read the story](/users/khan-academy) ## Magic Patterns > "When a customer pings us, we instantly open Langfuse. This allows keeping support resolution under 8 minutes." > > — Alexander Danilowicz, Co-founder [Read the story](/users/magic-patterns-ai-design-tools) ## Merck > "Langfuse enables us to track every prompt, response, cost, and latency in real time, turning black-box models into auditable, optimizable assets." > > — Walid Mehanna, Chief Data & AI Officer [Read the story](/users/merckgroup) ## SumUp > "Building on Langfuse we saved 30% of external BPO cost by deflecting 50% of support conversations to AI." > > — Ana Casado, Head of Operations Data and AI [Read the story](/users/sumup) ## Hugging Face > "In just a few minutes you're up and running, and you're already able to see what's going on." > > — Niels Rogge, Machine Learning Engineer [Read the story](/users/hugging-face) - **90B+** Observations / month - **21** of the Fortune 50 - **34k** GitHub stars - **100+** Integrations ## Learn from teams building AI on Langfuse ### [How Canva built an Agentic Support Experience using Langfuse](/users/canva) *Canva* > "Langfuse hits the sweet spot between engineering requirements and empowerment of non-technical users to contribute their domain expertise." ### [Khan Academy uses Langfuse's AI Engineering platform to build Khanmigo AI](/users/khan-academy) *Khan Academy* > "Langfuse has enabled our developers to get extremely fast feedback. It's fundamental to how our developers understand their AI implementations." ### [Building AI Design Tools at Scale](/users/magic-patterns-ai-design-tools) *Magic Patterns* > "When a customer pings us, we instantly open Langfuse. This allows keeping support resolution under 8 minutes." ### [How Merck is serving 80+ AI project teams globally on Langfuse](/users/merckgroup) *Merck* > "Langfuse enables us to track every prompt, response, cost, and latency in real time, turning black-box models into auditable, optimizable assets." ### [AI-Powered first level support for 4 million merchants](/users/sumup) *SumUp* > "Building on Langfuse we saved 30% of external BPO cost by deflecting 50% of support conversations to AI." ### [How Hugging Face Scales Open-Source Model Discovery with Agents and Langfuse](/users/hugging-face) *Hugging Face* > "In just a few minutes you're up and running, and you're already able to see what's going on." ### [How Cresta traces multi-service AI agent pipelines with Langfuse](/users/cresta) *Cresta* > "Langfuse has made it a lot easier for us at Cresta to iterate on LLM behavior. It has sped up how quickly we can test, learn, improve the model, and build great AI agents." ### [How Ravenna uses Langfuse to build and debug AI agents for enterprise internal support](/users/ravenna) *Ravenna* > "Building a product like ours would be impossible without Langfuse. Our agents handle hundreds of different systems and request types across different companies. Knowing what they do and knowing if it is going well is irreplaceable." ### [From a manual spreadsheet to 12x higher experimentation velocity: how Slite observes and evaluates its AI agents with Langfuse](/users/slite) *Slite* > "Having this data set, having this whole test suite that a developer can run on their machine and quickly get results, it's a game changer for us." ## Langfuse is adopted by 100,000+ developers worldwide Explore companies publicly using Langfuse and the sources describing how they use it. [Read customer stories](/users) The following list of companies using Langfuse and their success stories is assembled from public sources, thus might differ from current reality. We'd appreciate it if you share the story of adopting Langfuse in your company and add it to the list, but please make sure you won't have any NDA issues by doing so. Providing updates with publications from other companies is also useful. | Company | Use Case | Reference | | ---------------------------------------------------------------------------- | ----------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Accor](https://group.accor.com/) | Hospitality — AccorGPT, AI Butler, and TravelConcierge | Langfuse Customer | | [Adobe](https://www.adobe.com/) | Creative software and digital experience platform | [OSS LLMOps Stack](https://web.archive.org/web/20260304001459/https://oss-llmops-stack.com/) | | [Apple](https://www.apple.com/) | Consumer electronics and software | [Job Description](https://web.archive.org/web/20260304001155/https://jobs.apple.com/en-us/details/200646386-1052/ai-evaluation-engineer) | | [Base44](https://base44.com/) (Wix) | LLM logging for AI app-building platform | [Data Processing Addendum](https://3a44ea93-56d0-41e7-9974-8069d5d469b6.filesusr.com/ugd/7afb6c_1141f19f33cd4e1da17f3cb1214b71f5.pdf) ([Archive](https://web.archive.org/web/20260724075640/https://3a44ea93-56d0-41e7-9974-8069d5d469b6.filesusr.com/ugd/7afb6c_1141f19f33cd4e1da17f3cb1214b71f5.pdf)) | | [Bayer](https://www.bayer.com/) | Monitoring and evaluation of preclinical research chatbot | [Client Story](https://www.thoughtworks.com/clients/bayer-ag) ([Archive](https://web.archive.org/web/20260312105423/https://www.thoughtworks.com/clients/bayer-ag)) | | [Canva](https://www.canva.com/) | AI-powered support agent experience | [User Story](/users/canva) | | [Circleback](https://circleback.ai/) | AI meeting assistant with transcription and notes | Langfuse Customer | | [Cisco](https://www.cisco.com/) | Networking and cybersecurity | [Blogpost from 12/23/2025](https://web.archive.org/web/20260304001821/https://outshift.cisco.com/blog/komodor-automated-agent-creation) | | [City of Munich](https://stadt.muenchen.de/) | Tracing and monitoring of municipal AI applications | [Open Source Catalog](https://opensource.muenchen.de/software/langfuse.html) ([Archive](https://web.archive.org/web/20260701142807/https://opensource.muenchen.de/software/langfuse.html)) | | [Cornelsen](https://www.cornelsen.com/) | Educational publishing and learning solutions | [OSS LLMOps Stack](https://web.archive.org/web/20260304001459/https://oss-llmops-stack.com/) | | [CyberAgent](https://www.cyberagent.co.jp/en/) | Agent monitoring for AI Worker Platform | [Tech Blogpost](https://www.ai-shift.co.jp/techblog/6554) ([Archive](https://web.archive.org/web/20260122075353/https://www.ai-shift.co.jp/techblog/6554)) | | [Cybozu](https://cybozu.co.jp/) | Self-hosted LLM observability for kintone AI | [AWS Conference Deck](https://pages.awscloud.com/rs/112-TZM-766/images/R13_0625_3_ARC317_v1.pdf) ([Archive](https://web.archive.org/web/20260724075712/https://pages.awscloud.com/rs/112-TZM-766/images/R13_0625_3_ARC317_v1.pdf)) | | [Draftbit](https://www.draftbit.com/) | Visual mobile app development | Langfuse Customer | | [Ecosia](https://www.ecosia.org/) | Quality assurance for AI chat | [Privacy Policy](https://www.ecosia.org/privacy) ([Archive](https://web.archive.org/web/20260722150829/https://www.ecosia.org/privacy)) | | [Equinix](https://www.equinix.com/) | Tracing and evaluation of multi-agent network operations platform | [Research Paper](https://doi.org/10.20944/preprints202606.0915.v1) ([Archive](https://archive.ph/AuZ4g)) | | [Expedia Group](https://www.expediagroup.com/) | Travel technology platform | [Job Description](https://web.archive.org/web/20260304001608/https://careers.expediagroup.com/job/software-development-engineer-iii/seattle-WA/R-101417/) | | [Fletch](https://www.fletch.ai/) | Security and threat intelligence platform | [OSS LLMOps Stack](https://web.archive.org/web/20260304001459/https://oss-llmops-stack.com/) | | [freee](https://www.freee.co.jp/) | Self-hosted Langfuse v3 for LLM observability | [Tech Blogpost](https://developers.freee.co.jp/entry/clickhouse-hosting-options-on-aws) ([Archive](https://web.archive.org/web/20260305053015/https://developers.freee.co.jp/entry/clickhouse-hosting-options-on-aws)) | | [GoodData](https://www.gooddata.com/) | Dataset and experiment tracking for AI evaluation | [Blogpost](https://www.gooddata.ai/blog/evaluation-of-ai-applications-in-practice/) ([Archive](https://web.archive.org/web/20260513130516/https://www.gooddata.ai/blog/evaluation-of-ai-applications-in-practice/)) | | [Groupon](https://www.groupon.com/) | Standardized monitoring and tracing across AI workflows | [LinkedIn Post](https://www.linkedin.com/posts/alesdrabek_ai-cto-aiarchitecture-activity-7389763248734076929-1XOg) ([Archive](https://archive.ph/7BcPc)) | | [HP](https://www.hp.com/) | Self-hosted LLM observability at scale on AWS EKS | [LinkedIn Post](https://www.linkedin.com/posts/gajanan-chandgadkar_running-self-hosted-langfuse-at-scale-our-activity-7423772978091470848-9YJ-) ([Archive](https://archive.ph/7itKQ)) | | [Hugging Face](https://huggingface.co/) | Open source model discovery agent for Hugging Face Hub | [User Story](/users/hugging-face) | | [iFood](https://www.ifood.com.br/) | Observability for agentic threat hunting | [ClickHouse Blogpost](https://clickhouse.com/blog/ifood-agentic-security-platform#agentic-threat-hunting-with-clickhouse-and-langfuse) ([Archive](https://web.archive.org/web/20260814115309/https://clickhouse.com/blog/ifood-agentic-security-platform)) | | [Intel](https://www.intel.com/) | Observability for enterprise GenAI inference stack | [IT White Paper](https://media26.connectedsocialmedia.com/intel/21294/Cost_Effective_Scalable_Infrastructure_GenAI_Workloads.pdf) ([Archive](https://web.archive.org/web/20260305015903/https://media26.connectedsocialmedia.com/intel/21294/Cost_Effective_Scalable_Infrastructure_GenAI_Workloads.pdf)) | | [Intuit](https://www.intuit.com/) | Financial software (TurboTax, QuickBooks) | Langfuse Customer | | [Johns Hopkins University](https://www.jhu.edu/) | Observability for HopGPT enterprise AI platform | [Release Notes](https://hopgpt.it.jh.edu/2025-hopgpt-release-notes/) ([Archive](https://web.archive.org/web/20260514000057/https://hopgpt.it.jh.edu/2025-hopgpt-release-notes/)) | | [Juicebox](https://www.juicebox.ai/) | LLM latency monitoring and cost tracking | [Case Study](https://posthog.com/customers/juicebox) ([Archive](https://web.archive.org/web/20260512094929/https://posthog.com/customers/juicebox)) | | [KDDI](https://www.kddi.com/) | Tracing and prompt management for internal sales tool | [AWS Blogpost](https://aws.amazon.com/jp/blogs/news/aws-genai-usecases-kddi-agile-minutes/) ([Archive](https://web.archive.org/web/20260704041226/https://aws.amazon.com/jp/blogs/news/aws-genai-usecases-kddi-agile-minutes/)) | | [Kensho](https://kensho.com/) (S&P Global) | Operations stack for customer-facing AI applications | [Job Description](https://spgi.wd5.myworkdayjobs.com/en-US/Kensho_Careers/job/Senior-Full-Stack-Software-Engineer_324984) ([Archive](https://archive.ph/xFJ6x)) | | [Khan Academy](https://www.khanacademy.org/) | Free online education platform | [User Story](/users/khan-academy) | | [KINTO Technologies](https://www.kinto-technologies.com/) (Toyota Group) | LLM monitoring on shared internal platform | [Tech Blogpost](https://blog.kinto-technologies.com/posts/2025-12-14-monitoringplatform-renewal/) ([Archive](https://web.archive.org/web/20260415040050/https://blog.kinto-technologies.com/posts/2025-12-14-monitoringplatform-renewal/)) | | [Knowunity](https://www.knowunity.com/) | Educational technology | Langfuse Customer | | [Kombo](https://www.kombo.dev/) | Unified HR and payroll API | Langfuse Customer | | [La Suite numérique](https://lasuite.numerique.gouv.fr/) (French government) | Monitoring of AI actions in the Docs platform | [Release Notes](https://github.com/suitenumerique/docs/releases/tag/v4.4.0) ([Archive](https://web.archive.org/web/20260416035058/https://github.com/suitenumerique/docs/releases/tag/v4.4.0)) | | [Lemonade](https://www.lemonade.com/) | Insurance technology | [OSS LLMOps Stack](https://web.archive.org/web/20260304001459/https://oss-llmops-stack.com/) | | [Magic Patterns](https://www.magicpatterns.com/) | AI-powered UI design tool | [User Story](/users/magic-patterns-ai-design-tools) | | [McKinsey & Company](https://www.mckinsey.com/) | Agent observability in Agents at Scale marketplace | [Documentation](https://mckinsey.github.io/agents-at-scale-marketplace/services/langfuse/) ([Archive](https://web.archive.org/web/20260724080128/https://mckinsey.github.io/agents-at-scale-marketplace/services/langfuse/)) | | [Merck Group](https://www.merckgroup.com/) | Pharmaceutical and life sciences | [User Story](/users/merckgroup) | | [Mitsubishi Heavy Industries](https://www.mhi.com/) | Company-wide RAG quality evaluation | [Conference Deck](https://speakerdeck.com/haradasn/quan-she-ragnojing-du-tietuku-ezientoniwan-tou-gesitemitahua) ([Archive](https://web.archive.org/web/20260724080013/https://speakerdeck.com/haradasn/quan-she-ragnojing-du-tietuku-ezientoniwan-tou-gesitemitahua)) | | [Moderna](https://www.modernatx.com/) | AI observability, prompt analytics, and debugging | [Job Description](https://modernatx.wd1.myworkdayjobs.com/en-US/M_tx/job/Warsaw---Poland/Senior-Observability-Engineer_R19439) ([Archive](https://archive.ph/BQn9j)) | | [Monzo](https://monzo.com/) | AI observability and evaluation on ML platform | [Job Description](https://job-boards.greenhouse.io/monzo/jobs/8020007) ([Archive](https://web.archive.org/web/20260724080148/https://job-boards.greenhouse.io/monzo/jobs/8020007)) | | [NASA](https://www.nasa.gov/) | Observability for mission-critical RAG platform (AMPLIFY) | [Technical Memorandum](https://ntrs.nasa.gov/api/citations/20260000162/downloads/AMPLIFY%20LLM%20Platform%20Whitepaper_final.pdf) ([Archive](https://web.archive.org/web/20260724080233/https://ntrs.nasa.gov/api/citations/20260000162/downloads/AMPLIFY%20LLM%20Platform%20Whitepaper_final.pdf)) | | [Pigment](https://www.pigment.com/) | Enterprise business planning | Langfuse Customer | | [Pipedream](https://pipedream.com/) (Workday) | AI application monitoring | [Subprocessor List](https://pipedream.com/docs/subprocessors) ([Archive](https://web.archive.org/web/20260422112230/https://pipedream.com/docs/subprocessors)) | | [Posit](https://posit.co/) | Tracing for Shiny Assistant | [Source Code](https://github.com/posit-dev/shiny-assistant/blob/main/shinyapp/app.py) ([Archive](https://web.archive.org/web/20260724080358/https://github.com/posit-dev/shiny-assistant/blob/main/shinyapp/app.py)) | | [Ramp](https://ramp.com/) | Corporate spend management and finance platform | Langfuse Customer | | [Rocket Money](https://www.rocketmoney.com/) | Personal finance and subscription management | [OSS LLMOps Stack](https://web.archive.org/web/20260304001459/https://oss-llmops-stack.com/) | | [Salesloft](https://www.salesloft.com/) | Agent tracing, evaluation, and prompt management | [Conference Talk](https://2025.allthingsopen.org/sessions/2-for-1-ai-powered-integration-the-future-of-natural-programming-and-intelligent-connectivity-actionable-llm-agent-observability-with-langfuse) ([Archive](https://web.archive.org/web/20251006203117/https://2025.allthingsopen.org/sessions/2-for-1-ai-powered-integration-the-future-of-natural-programming-and-intelligent-connectivity-actionable-llm-agent-observability-with-langfuse)) | | [Samsara](https://www.samsara.com/) | Monitoring and optimization of Samsara Assistant | [AWS Blogpost](https://aws.amazon.com/blogs/apn/transform-large-language-model-observability-with-langfuse/) ([Archive](https://web.archive.org/web/20260630024906/https://aws.amazon.com/blogs/apn/transform-large-language-model-observability-with-langfuse/)) | | [Sanofi](https://www.sanofi.com/) | Quality monitoring for agentic AI deployment | [Partner Newsletter](https://www.artefact.com/nl/pdf-newsletters/may-news-reimagining-marketing-with-ai-agents-client-cases-bouygues/) ([Archive](https://web.archive.org/web/20260724080305/https://www.artefact.com/nl/pdf-newsletters/may-news-reimagining-marketing-with-ai-agents-client-cases-bouygues/)) | | [Seven Eleven Japan](https://www.sej.co.jp/en/) | Convenience retail | Langfuse Customer | | [Slite](https://slite.com/) | Observability and evals for a self-maintaining knowledge agent | [User Story](/users/slite) | | [SumUp](https://www.sumup.com/) | Point-of-sale and payment processing | [User Story](/users/sumup) | | [TELUS](https://www.telus.com/) | Canadian telecommunications | Langfuse Customer | | [The Weather Company](https://www.weathercompany.com/) | Weather intelligence and forecasting services | [OSS LLMOps Stack](https://web.archive.org/web/20260304001459/https://oss-llmops-stack.com/) | | [Twilio](https://www.twilio.com/) | Collaborative prompt management | [AWS Blogpost](https://aws.amazon.com/blogs/apn/transform-large-language-model-observability-with-langfuse/) ([Archive](https://web.archive.org/web/20260630024906/https://aws.amazon.com/blogs/apn/transform-large-language-model-observability-with-langfuse/)) | ## Ready to get started with Langfuse? Join thousands of teams building better LLM applications with Langfuse's open-source observability platform. - [Start free](/cloud) - [Documentation](/docs) - [Talk to an expert](/talk-to-us) --- ## 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/users.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 .