{"content_id":"xvqhnc4puu","slug":"mistral-ai-studio-expands-managed-agents-public-preview","locale":"en","schema_type":"NewsArticle","category":"news","category_name":"News","title":"Mistral AI Studio Adds Agents in Public Preview","summary":"Mistral AI added managed agents and apps to Studio and expanded workflow, tracing, and evaluation features. Agents and workflows are in public preview; availability in Korea and separate execution fees have not been confirmed.","sponsorship_disclosure":null,"affiliate_disclosure":null,"commerce_disclosure":null,"author":{"name":"Injoys Editorial Team","url":"https://injoys.com/ko/about"},"key_points":["On November 5, 2026, Mistral AI announced the addition of managed agents and apps to Studio and the expansion of related features.","Managed Agents, Agents SDK, and Mistral Workflows are in public preview and remain subject to change.","Apps cannot be created on Free or on Pro and Team plans without pay-as-you-go billing enabled.","Mistral Large 4 API pricing is $0.7 per 1 million input tokens and $2.1 per 1 million output tokens.","Sign-up, payment, and service availability in Korea, as well as support for data storage in Korea, have not been confirmed."],"content_markdown":"Mistral AI announced an expansion of Studio on November 5, 2026. It added managed agents and apps. Agents are in public preview, and app creation is restricted by plan. Availability in Korea was not specified.\n\nThis article follows Mistral AI's announcement and official documentation, checked as of November 6, 2026.\n\n## Managed agents and apps added to Studio\n\nMistral AI said it had expanded Studio's development and deployment features. The announcement introduced managed agents and apps. Workflow and enterprise context features were also part of the expansion. Agent observability and evaluation features were included as well.\n\nLe Chonk is the name of the Mistral Large 4 model. The company introduced it as a native multimodal model in public preview. Studio serves as the environment for developing and running agents and apps.\n\nThe official release notes explained how the workflow builder works. It turns tasks described in natural language into working workflows. Vibe handles authoring, testing, and deployment.\n\n## Agents and workflows in public preview, with feature-specific access conditions\n\nManaged Agents and Agents SDK are in public preview. Mistral Workflows is also available in public preview. The official documentation separately specifies possible changes and access conditions for each product.\n\n| Feature | Release status or access conditions | Official documentation's description |\n| --- | --- | --- |\n| Managed Agents and Agents SDK | Public preview | APIs, behavior, and limits may change |\n| Mistral Workflows | Public preview | No major changes are planned, but APIs and features may still change |\n| Agent and workflow execution | Mistral cloud or your own infrastructure | Both execution environments are supported |\n| Tracing and evaluation | Enterprise-tier organizations only | Restrictions apply based on organization tier |\n| App creation | Restricted by plan and whether pay-as-you-go billing is enabled | Unavailable on Free or on Pro and Team without pay-as-you-go billing enabled |\n\nAccording to the Studio documentation, tracing and evaluation are available only to **Enterprise-tier organizations**. The conditions for running agents must be distinguished from those for using tracing and evaluation. Whether users can sign up or use the service in Korea was not specified.\n\n## Model API pricing and app configuration limits disclosed\n\nThe official API pricing table lists separate input and output rates for Mistral Large 4. The prices below were checked as of November 6, 2026. Separate rates for running managed agents, workflows, and apps were not confirmed.\n\n| Billing item | Unit | Official listed price |\n| --- | --- | --- |\n| Mistral Large 4 input | 1 million tokens | $0.7 |\n| Mistral Large 4 output | 1 million tokens | $2.1 |\n\nThese prices alone cannot be used to calculate the total cost of operating Studio. Model API charges and managed execution costs must be checked separately. The fact that separate execution rates were not confirmed does not mean execution is free.\n\nA single app can have **at most 3 frontends and backends combined**. The official managed app documentation excludes workers from this limit. This does not mean that 3 frontends and 3 backends are allowed.\n\nOn Free, users cannot create apps even if deployment commands are visible. The same restriction applies to Pro and Team without pay-as-you-go billing enabled. App deployment permissions should not be judged solely by whether commands are displayed.\n\n## Model size figures are self-reported by Mistral AI\n\nThe size figures for Mistral Large 4 are specifications listed in the company's model card. Active parameters and total parameters are separate items. The figures below are not performance measurements from an independent organization.\n\n| Model card item | Listed figure | Korean quantity notation |\n| --- | --- | --- |\n| Active parameters | 52B | 52 billion |\n| Total parameters | 1.05T | 1 trillion 50 billion |\n| Vision encoder | 1.6B | 1.6 billion |\n\nMistral AI's model introduction describes Le Chonk as a 1 trillion-parameter model. The model card gives a more specific total parameter count of 1.05T. These numbers alone cannot establish accuracy on Korean-language tasks or execution speed.\n\n## Korea support, execution pricing, and general availability schedule remain unconfirmed\n\nThe official sources checked did not specify some conditions needed for adoption in Korea. The end date for the public preview was also not confirmed. Public preview should not be treated as general availability.\n\n- Availability of sign-up, payment, and service in Korea\n- Support for a Korean region and data storage within Korea\n- Separate billing rates for running managed agents, workflows, and apps\n- Schedule for the end of public preview and general availability\n- Exact announcement time and time zone for Studio's new features\n\nThe publication date associated with the announcement is November 5, 2026. The exact announcement time and the company's reference time zone were not confirmed. The announcement time converted to Korean time therefore cannot be established either.\n\n## Check account, cost, and data conditions before adoption in Korea\n\nBefore adopting the service in Korea, first check whether it is available there. Support for running on your own infrastructure does not, by itself, guarantee data storage within Korea. Before paying, it is advisable to check the following items in the official documentation and with the company.\n\n- Whether Korean accounts can sign up, pay, and use the service\n- App creation permissions and conditions for enabling pay-as-you-go billing on the intended plan\n- Whether the Enterprise tier required for tracing and evaluation applies\n- Execution costs incurred in addition to model API charges\n- Data storage locations for each execution environment and support for a Korean region\n- Whether you can respond to changes in APIs, behavior, and limits during preview","content_html":"\u003cp\u003eMistral AI announced an expansion of Studio on November 5, 2026. It added managed agents and apps. Agents are in public preview, and app creation is restricted by plan. Availability in Korea was not specified.\u003c/p\u003e\n\u003cp\u003eThis article follows Mistral AI's announcement and official documentation, checked as of November 6, 2026.\u003c/p\u003e\n\u003ch2\u003e\n\u003ca href=\"#managed-agents-and-apps-added-to-studio\" class=\"anchor\" id=\"managed-agents-and-apps-added-to-studio\"\u003e\u003c/a\u003eManaged agents and apps added to Studio\u003c/h2\u003e\n\u003cp\u003eMistral AI said it had expanded Studio's development and deployment features. The announcement introduced managed agents and apps. Workflow and enterprise context features were also part of the expansion. Agent observability and evaluation features were included as well.\u003c/p\u003e\n\u003cp\u003eLe Chonk is the name of the Mistral Large 4 model. The company introduced it as a native multimodal model in public preview. Studio serves as the environment for developing and running agents and apps.\u003c/p\u003e\n\u003cp\u003eThe official release notes explained how the workflow builder works. It turns tasks described in natural language into working workflows. Vibe handles authoring, testing, and deployment.\u003c/p\u003e\n\u003ch2\u003e\n\u003ca href=\"#agents-and-workflows-in-public-preview-with-feature-specific-access-conditions\" class=\"anchor\" id=\"agents-and-workflows-in-public-preview-with-feature-specific-access-conditions\"\u003e\u003c/a\u003eAgents and workflows in public preview, with feature-specific access conditions\u003c/h2\u003e\n\u003cp\u003eManaged Agents and Agents SDK are in public preview. Mistral Workflows is also available in public preview. The official documentation separately specifies possible changes and access conditions for each product.\u003c/p\u003e\n\u003cdiv class=\"overflow-x-auto\"\u003e\u003ctable\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth\u003eFeature\u003c/th\u003e\n\u003cth\u003eRelease status or access conditions\u003c/th\u003e\n\u003cth\u003eOfficial documentation's description\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Feature\"\u003eManaged Agents and Agents SDK\u003c/td\u003e\n\u003ctd data-label=\"Release status or access conditions\"\u003ePublic preview\u003c/td\u003e\n\u003ctd data-label=\"Official documentation's description\"\u003eAPIs, behavior, and limits may change\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Feature\"\u003eMistral Workflows\u003c/td\u003e\n\u003ctd data-label=\"Release status or access conditions\"\u003ePublic preview\u003c/td\u003e\n\u003ctd data-label=\"Official documentation's description\"\u003eNo major changes are planned, but APIs and features may still change\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Feature\"\u003eAgent and workflow execution\u003c/td\u003e\n\u003ctd data-label=\"Release status or access conditions\"\u003eMistral cloud or your own infrastructure\u003c/td\u003e\n\u003ctd data-label=\"Official documentation's description\"\u003eBoth execution environments are supported\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Feature\"\u003eTracing and evaluation\u003c/td\u003e\n\u003ctd data-label=\"Release status or access conditions\"\u003eEnterprise-tier organizations only\u003c/td\u003e\n\u003ctd data-label=\"Official documentation's description\"\u003eRestrictions apply based on organization tier\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Feature\"\u003eApp creation\u003c/td\u003e\n\u003ctd data-label=\"Release status or access conditions\"\u003eRestricted by plan and whether pay-as-you-go billing is enabled\u003c/td\u003e\n\u003ctd data-label=\"Official documentation's description\"\u003eUnavailable on Free or on Pro and Team without pay-as-you-go billing enabled\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\u003c/div\u003e\n\u003cp\u003eAccording to the Studio documentation, tracing and evaluation are available only to \u003cstrong\u003eEnterprise-tier organizations\u003c/strong\u003e. The conditions for running agents must be distinguished from those for using tracing and evaluation. Whether users can sign up or use the service in Korea was not specified.\u003c/p\u003e\n\u003ch2\u003e\n\u003ca href=\"#model-api-pricing-and-app-configuration-limits-disclosed\" class=\"anchor\" id=\"model-api-pricing-and-app-configuration-limits-disclosed\"\u003e\u003c/a\u003eModel API pricing and app configuration limits disclosed\u003c/h2\u003e\n\u003cp\u003eThe official API pricing table lists separate input and output rates for Mistral Large 4. The prices below were checked as of November 6, 2026. Separate rates for running managed agents, workflows, and apps were not confirmed.\u003c/p\u003e\n\u003cdiv class=\"overflow-x-auto\"\u003e\u003ctable\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth\u003eBilling item\u003c/th\u003e\n\u003cth\u003eUnit\u003c/th\u003e\n\u003cth\u003eOfficial listed price\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Billing item\"\u003eMistral Large 4 input\u003c/td\u003e\n\u003ctd data-label=\"Unit\"\u003e1 million tokens\u003c/td\u003e\n\u003ctd data-label=\"Official listed price\"\u003e$0.7\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Billing item\"\u003eMistral Large 4 output\u003c/td\u003e\n\u003ctd data-label=\"Unit\"\u003e1 million tokens\u003c/td\u003e\n\u003ctd data-label=\"Official listed price\"\u003e$2.1\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\u003c/div\u003e\n\u003cp\u003eThese prices alone cannot be used to calculate the total cost of operating Studio. Model API charges and managed execution costs must be checked separately. The fact that separate execution rates were not confirmed does not mean execution is free.\u003c/p\u003e\n\u003cp\u003eA single app can have \u003cstrong\u003eat most 3 frontends and backends combined\u003c/strong\u003e. The official managed app documentation excludes workers from this limit. This does not mean that 3 frontends and 3 backends are allowed.\u003c/p\u003e\n\u003cp\u003eOn Free, users cannot create apps even if deployment commands are visible. The same restriction applies to Pro and Team without pay-as-you-go billing enabled. App deployment permissions should not be judged solely by whether commands are displayed.\u003c/p\u003e\n\u003ch2\u003e\n\u003ca href=\"#model-size-figures-are-self-reported-by-mistral-ai\" class=\"anchor\" id=\"model-size-figures-are-self-reported-by-mistral-ai\"\u003e\u003c/a\u003eModel size figures are self-reported by Mistral AI\u003c/h2\u003e\n\u003cp\u003eThe size figures for Mistral Large 4 are specifications listed in the company's model card. Active parameters and total parameters are separate items. The figures below are not performance measurements from an independent organization.\u003c/p\u003e\n\u003cdiv class=\"overflow-x-auto\"\u003e\u003ctable\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth\u003eModel card item\u003c/th\u003e\n\u003cth\u003eListed figure\u003c/th\u003e\n\u003cth\u003eKorean quantity notation\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Model card item\"\u003eActive parameters\u003c/td\u003e\n\u003ctd data-label=\"Listed figure\"\u003e52B\u003c/td\u003e\n\u003ctd data-label=\"Korean quantity notation\"\u003e52 billion\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Model card item\"\u003eTotal parameters\u003c/td\u003e\n\u003ctd data-label=\"Listed figure\"\u003e1.05T\u003c/td\u003e\n\u003ctd data-label=\"Korean quantity notation\"\u003e1 trillion 50 billion\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Model card item\"\u003eVision encoder\u003c/td\u003e\n\u003ctd data-label=\"Listed figure\"\u003e1.6B\u003c/td\u003e\n\u003ctd data-label=\"Korean quantity notation\"\u003e1.6 billion\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\u003c/div\u003e\n\u003cp\u003eMistral AI's model introduction describes Le Chonk as a 1 trillion-parameter model. The model card gives a more specific total parameter count of 1.05T. These numbers alone cannot establish accuracy on Korean-language tasks or execution speed.\u003c/p\u003e\n\u003ch2\u003e\n\u003ca href=\"#korea-support-execution-pricing-and-general-availability-schedule-remain-unconfirmed\" class=\"anchor\" id=\"korea-support-execution-pricing-and-general-availability-schedule-remain-unconfirmed\"\u003e\u003c/a\u003eKorea support, execution pricing, and general availability schedule remain unconfirmed\u003c/h2\u003e\n\u003cp\u003eThe official sources checked did not specify some conditions needed for adoption in Korea. The end date for the public preview was also not confirmed. Public preview should not be treated as general availability.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eAvailability of sign-up, payment, and service in Korea\u003c/li\u003e\n\u003cli\u003eSupport for a Korean region and data storage within Korea\u003c/li\u003e\n\u003cli\u003eSeparate billing rates for running managed agents, workflows, and apps\u003c/li\u003e\n\u003cli\u003eSchedule for the end of public preview and general availability\u003c/li\u003e\n\u003cli\u003eExact announcement time and time zone for Studio's new features\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eThe publication date associated with the announcement is November 5, 2026. The exact announcement time and the company's reference time zone were not confirmed. The announcement time converted to Korean time therefore cannot be established either.\u003c/p\u003e\n\u003ch2\u003e\n\u003ca href=\"#check-account-cost-and-data-conditions-before-adoption-in-korea\" class=\"anchor\" id=\"check-account-cost-and-data-conditions-before-adoption-in-korea\"\u003e\u003c/a\u003eCheck account, cost, and data conditions before adoption in Korea\u003c/h2\u003e\n\u003cp\u003eBefore adopting the service in Korea, first check whether it is available there. Support for running on your own infrastructure does not, by itself, guarantee data storage within Korea. Before paying, it is advisable to check the following items in the official documentation and with the company.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eWhether Korean accounts can sign up, pay, and use the service\u003c/li\u003e\n\u003cli\u003eApp creation permissions and conditions for enabling pay-as-you-go billing on the intended plan\u003c/li\u003e\n\u003cli\u003eWhether the Enterprise tier required for tracing and evaluation applies\u003c/li\u003e\n\u003cli\u003eExecution costs incurred in addition to model API charges\u003c/li\u003e\n\u003cli\u003eData storage locations for each execution environment and support for a Korean region\u003c/li\u003e\n\u003cli\u003eWhether you can respond to changes in APIs, behavior, and limits during preview\u003c/li\u003e\n\u003c/ul\u003e\n","tags":["Generative AI","AI Agents","AI Development","Development Tools"],"faqs":[{"question":"Can the new Studio features be used right away in Korea as well?","answer":"Official sources do not specify whether sign-up, payment, and service are available in Korea. Support for a Korea region and data storage within Korea has also not been confirmed, so you should check with the company before adopting it."},{"question":"Can you build and deploy apps on the Free plan?","answer":"According to the Studio app documentation, you cannot create apps on Free even if you can see deployment commands. The same restriction applies to Pro and Team if pay-as-you-go billing is not enabled."},{"question":"Can operating costs be calculated using only the Mistral Large 4 API pricing?","answer":"Input costs $0.7 per 1 million tokens, and output costs $2.1 per 1 million tokens. Separate rates for running managed agents, workflows, and apps have not been confirmed, so this pricing alone cannot be used to calculate total operating costs."}],"sources":[{"url":"https://mistral.ai/news/build-with-studio/","title":"Le Chonk brings the brains. Studio puts it to work. - Mistral AI","type":"source"},{"url":"https://mistral.ai/news/mistral-large-4-oss/","title":"Mistral Large 4 (Le Chonk) is now open weight - Mistral AI","type":"source"},{"url":"https://docs.mistral.ai/studio/agents/overview","title":"Managed Agents | Mistral Docs - Mistral AI","type":"source"},{"url":"https://docs.mistral.ai/resources/release-notes","title":"Release notes | Mistral Docs - Mistral AI","type":"source"},{"url":"https://docs.mistral.ai/studio/workflows/overview","title":"Overview | Mistral Docs - Mistral AI","type":"source"},{"url":"https://docs.mistral.ai/studio","title":"Studio | Mistral Docs - Mistral AI","type":"source"},{"url":"https://docs.mistral.ai/studio/apps/overview","title":"Apps overview | Mistral Docs - Mistral AI","type":"source"},{"url":"https://docs.mistral.ai/studio/deployments/managed/apps","title":"Deploy apps with managed deployments | Mistral Docs - Mistral AI","type":"source"},{"url":"https://docs.mistral.ai/inference/pricing","title":"API pricing | Mistral Docs - Mistral AI","type":"source"},{"url":"https://docs.mistral.ai/models/mistral-large-4-0","title":"Mistral Large 4 - Mistral AI | Mistral Docs - Mistral AI","type":"source"}],"images":[{"id":2472,"url":"https://injoys.com/rails/active_storage/blobs/proxy/eyJfcmFpbHMiOnsiZGF0YSI6Mzg0NjQsInB1ciI6ImJsb2JfaWQifX0=--69bd002e677addff6121ae219d07e6df4704afff/ai-034cade6.webp","is_representative":true,"generation_method":"ai_photo","license":"ai_generated","mime_type":"image/webp","width":1536,"height":1024,"translations":{"ko":{"alt":"데이터센터에서 파란 작업복을 입은 여성 엔지니어가 랙에서 꺼낸 서버 내부를 점검하고 있다.","caption":"Mistral AI가 Studio의 관리형 에이전트와 워크플로를 공개 프리뷰로 제공한다.","description":null},"en":{"alt":"A woman engineer in blue workwear inspects a server pulled out from a rack in a data center.","caption":"Mistral AI is bringing managed agents and workflows to Studio in public preview.","description":null},"ja":{"alt":"データセンターで青い作業着の女性エンジニアが、ラックから引き出したサーバーの内部を点検している。","caption":"Mistral AIは、Studioでマネージドエージェントとワークフローをパブリックプレビューとして提供する。","description":null},"es":{"alt":"Una ingeniera con ropa de trabajo azul inspecciona un servidor extraído de un rack en un centro de datos.","caption":"Mistral AI incorpora agentes gestionados y flujos de trabajo a Studio en versión preliminar pública.","description":null},"id":{"alt":"Insinyur perempuan berseragam biru memeriksa server yang ditarik keluar dari rak di pusat data.","caption":"Mistral AI menghadirkan agen terkelola dan alur kerja di Studio dalam pratinjau publik.","description":null},"pt":{"alt":"Uma engenheira com uniforme azul inspeciona um servidor retirado de um rack em um centro de dados.","caption":"A Mistral AI traz agentes gerenciados e fluxos de trabalho ao Studio em prévia pública.","description":null},"zh-hant":{"alt":"一名穿著藍色工作服的女性工程師，在資料中心檢查從機架拉出的伺服器內部。","caption":"Mistral AI 在 Studio 推出受管代理與工作流程的公開預覽版。","description":null},"de":{"alt":"Eine Ingenieurin in blauer Arbeitskleidung prüft einen aus dem Rack gezogenen Server im Rechenzentrum.","caption":"Mistral AI führt verwaltete Agenten und Workflows in Studio als öffentliche Vorschau ein.","description":null}}},{"id":2473,"url":"https://injoys.com/rails/active_storage/blobs/proxy/eyJfcmFpbHMiOnsiZGF0YSI6Mzg0NjcsInB1ciI6ImJsb2JfaWQifX0=--06d7b31138a271f91f7d8b467f2fc0079fb5d258/ai-1c094ba6.webp","is_representative":false,"generation_method":"ai_semi","license":"ai_generated","mime_type":"image/webp","width":1536,"height":1024,"translations":{"ko":{"alt":"여러 모바일 기기가 놓인 테스트 공간에서 태블릿의 워크플로 화면을 살펴보는 남성","caption":"Mistral AI는 Studio의 워크플로·추적·평가 기능을 확장했다.","description":null},"en":{"alt":"A man examines a workflow on a tablet at a testing bench, with mobile devices on shelves behind him.","caption":"Mistral AI has expanded Studio’s workflow, tracing and evaluation capabilities.","description":null},"ja":{"alt":"モバイル端末が並ぶテストスペースで、タブレットのワークフロー画面を確認する男性","caption":"Mistral AIはStudioのワークフロー、トレース、評価機能を拡充した。","description":null},"es":{"alt":"Un hombre revisa un flujo de trabajo en una tableta, con dispositivos móviles en estantes detrás.","caption":"Mistral AI amplió las funciones de flujos de trabajo, trazabilidad y evaluación de Studio.","description":null},"id":{"alt":"Seorang pria memeriksa alur kerja di tablet pada meja pengujian, dengan perangkat seluler di rak belakangnya.","caption":"Mistral AI memperluas kemampuan alur kerja, pelacakan, dan evaluasi di Studio.","description":null},"pt":{"alt":"Um homem examina um fluxo de trabalho em um tablet, com dispositivos móveis nas prateleiras ao fundo.","caption":"A Mistral AI ampliou os recursos de fluxos de trabalho, rastreamento e avaliação do Studio.","description":null},"zh-hant":{"alt":"一名男子在測試工作檯前查看平板上的工作流程，身後架上擺放多部行動裝置","caption":"Mistral AI 擴充了 Studio 的工作流程、追蹤與評估功能。","description":null},"de":{"alt":"Ein Mann prüft einen Workflow auf einem Tablet an einem Testtisch, dahinter Regale mit Mobilgeräten.","caption":"Mistral AI hat die Workflow-, Tracing- und Evaluierungsfunktionen von Studio erweitert.","description":null}}}],"published_at":"2026-11-06T01:30:59+09:00","updated_at":"2026-11-06T01:30:59+09:00","license":"cc_by","translation_status":"reviewed","available_locales":["ko","en","ja","es"],"data_locales":["ko","en","ja","es","id","pt","zh-hant","de"],"url":"https://injoys.com/en/articles/mistral-ai-studio-expands-managed-agents-public-preview"}