# Langdock Commercial AI platform from Berlin with chat, agents, workflows and integrations for company-wide use. Canonical profile: https://ki-agentenkompass.de/en/agents/langdock/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-11-05 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Langdock is a proprietary product of Langdock GmbH in Berlin. The platform combines models from several providers; agents and workflows are parts alongside chat, meetings and apps. - Provider: Langdock GmbH - Product family: Langdock - Profile type: AI platform for companies with agents and workflows - Environment: Web interface, agents also in Slack and Teams; external access through an API and its own MCP server - Connections: According to the page 57 integrations, including Airtable, Asana, GitHub, GitLab and Azure DevOps, plus custom integrations and MCP servers - Setup: Start a trial without a credit card. For agents with actions you set up connections, and an admin must enable workflows. - Pricing model: Core EUR 23.20 and Work EUR 31.20 per seat per month excluding VAT; Enterprise is custom from 1,000 users. ## Key features ### Agents with knowledge and actions An agent combines instructions, a model, up to 50 files and actions through integrations, such as updating CRM entries or creating tickets. The documentation describes agents as specialised chatbots with tools. Source: https://docs.langdock.com/en/using-langdock/agents/configuration.md ### Workflows with triggers and nodes Workflows connect agents, integrations and custom logic into multi-step processes with conditions and loops. They start from a form, a schedule or an event in a connected app. Source: https://docs.langdock.com/en/using-langdock/workflows/introduction.md ### Scheduled tasks A saved prompt runs daily, on weekdays, weekly or monthly, optionally with an agent. Each user can have 10 tasks per workspace, and starts can be delayed by up to 15 minutes. Source: https://docs.langdock.com/en/using-langdock/chat/scheduled.md ### Integrations and MCP The page lists 57 integrations and 754 native actions. External MCP servers can be connected; up to 60 tools and 50 resources can be enabled per integration. Source: https://docs.langdock.com/en/using-langdock/guides/integrations/mcp/mcp.md ### Approval steps in workflows The "User input" node pauses a run until someone with editor access approves, rejects or submits a form. The run then continues on the matching branch. Source: https://docs.langdock.com/en/using-langdock/workflows/fundamentals/human-in-the-loop.md ### Governance for agents According to the page, admins can approve, flag or disable agent versions. Sharing with a team or the whole workspace can require approval. Source: https://www.langdock.com/products/governance ### Deployment options The default is multi-tenant SaaS on Microsoft Azure in the EU. According to the page, single-tenant starts at 2,000 seats, and your own cloud or on-premise via Helm charts at 5,000 seats. Source: https://www.langdock.com/security ## Example workflows ### Pre-sort incoming email - Your input: A workflow with an event trigger, an agent node and an approval step. - Possible result: The agent classifies the email and creates a draft reply that waits for approval. - What to check: Review inputs and outputs per node in the run and choose the error option for each node deliberately. ### Weekly briefing - Your input: A scheduled task with a selected agent and its knowledge. - Possible result: Each run creates a new chat with the summary, which you can open and continue. - What to check: Check whether actions need confirmation, because a waiting run counts as "Failed". ## Requirements and limits ### Workflows need an admin and a plan Requirement: An admin must enable workflows in the workspace settings. According to the pricing page they require an active Core or Work plan for all users, and they use AI credits. Source: https://www.langdock.com/pricing ### Memory does not apply in agent chats Limitation: Memory is available only in regular chats, not in project or agent chats. It holds at most 50 entries. Source: https://docs.langdock.com/en/using-langdock/chat/tools/memory.md ### MCP tools without default confirmation Limitation: Newly saved MCP tools do not require confirmation by default. You have to enable it for each tool afterwards. Source: https://docs.langdock.com/en/using-langdock/guides/integrations/mcp/mcp.md ### No built-in MFA Limitation: According to the documentation, Langdock has no standalone MFA. With SAML, MFA is enforced in the identity provider. Source: https://docs.langdock.com/en/admin/security/saml/saml.md ### Sub-processors not readable Not yet confirmed: The privacy policy points to the Trust Center for the list. The Trust Center returned only its title when fetched, so we could not check the names. Source: https://trust.langdock.com/ ### Model region labels Not yet confirmed: The models page marks models with an EU or globe symbol, for example Gemini 3.5 Flash and DeepSeek v3.1 with a globe. It does not explain what the globe symbol means for data processing. Source: https://www.langdock.com/models ## A good fit if … - you want chat, agents and workflows with several models on one platform for the whole company - processes should run on a schedule or event and wait for human approval at fixed points - admins should control agent versions and connections centrally ## Less suitable if … - you want to check the sub-processors on a freely readable page before signing - your company is well below 5,000 seats and wants to operate the platform itself - agents should remember things across sessions through memory Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Open choice By default you choose from Langdock's list of several providers. With your own keys (BYOK) you can also connect any OpenAI-compatible endpoint, such as LiteLLM, vLLM or Ollama; you select BYOK when moving to a paid plan or later through the Langdock team. The endpoint must be publicly reachable over HTTPS; internal addresses only work through support. - Model families named: Google (Gemini), OpenAI (GPT), Anthropic (Claude), Meta (Llama, Muse), Mistral, DeepSeek · Other models can be connected freely - Model choice: You choose - Your own API key: Yes - Router or custom endpoint: Yes - Local models: Yes - Depends on: Plan, Admin approval Documented · Sources accessed on: 2026-11-05 - [Langdock: Models](https://www.langdock.com/models) - [Langdock: BYOK](https://docs.langdock.com/en/admin/byok/byok.md) - [Langdock: BYOK setup guides](https://docs.langdock.com/en/admin/byok/setup-guides) ## Europe & regional availability Security page, models page, privacy policy and documentation reviewed. The Trust Center with the DPA, certificates and sub-processors returned only its title when fetched. Reviewed scope: Hosted platform in the EU; models depending on selection Reviewed on: 2026-11-05 ### Hosting in the EU Available According to the security page the multi-tenant SaaS runs on Microsoft Azure on servers in the EU. According to the page the application and "most" models are fully hosted in the EU, configurable. Region covered: EU Documented reason: Provider statement; the page does not specify the Azure data centre further. Official source: https://www.langdock.com/security ### Models outside the EU label With requirements The models page shows models from OpenAI, Anthropic, Google, Meta, Mistral and DeepSeek with an EU or globe symbol. GPT-5 Pro, Llama 4 Maverick and DeepSeek v3.1, for example, carry a globe. With BYOK you use your own keys with providers such as Azure, Anthropic or Google. Region covered: EU and beyond Documented reason: Processing depends on the model chosen; the page does not explain the globe symbol. Official source: https://www.langdock.com/models Official source: https://docs.langdock.com/en/admin/byok/byok.md ### Data processing agreement Available According to the documentation the data processing agreement is part of the terms and applies automatically with use. The document itself is in the Trust Center and could not be read. Region covered: EU/EEA Documented reason: Existence of the agreement is documented; its content was not reviewed. Official source: https://docs.langdock.com/en/admin/compliance-and-governance/legal-compliance.md Official source: https://trust.langdock.com/ ### Sub-processors and third countries Availability still unclear The privacy policy allows transfers to third countries outside the EU and EEA with suitable safeguards and points to the Trust Center for sub-processors. We could not read any names. Region covered: EU/EEA Documented reason: Trust Center not readable when fetched. Official source: https://www.langdock.com/privacy-policy Official source: https://trust.langdock.com/ ### Certificates and "GDPR compliant" Availability still unclear The security page mentions ISO 27001 and SOC 2 Type II with independent audit as well as "GDPR compliant". According to the documentation the certificates are in the Trust Center. "GDPR compliant" is a provider claim with no audit report on the page. Region covered: EU/EEA Documented reason: Certificates not seen; no authority assessment found. Official source: https://www.langdock.com/security Official source: https://docs.langdock.com/en/admin/compliance-and-governance/legal-compliance.md ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Hosted platform with workspace administration Sources reviewed: 2026-11-05 ### Account used Documented: According to the documentation SAML 2.0 works with any compatible identity provider, with guides for Entra ID, Google Workspace and Okta. SAML is mandatory for verified domains. According to the pricing page SSO, SCIM and SAML are in every plan. Evidence: https://docs.langdock.com/en/admin/security/saml/saml.md Evidence: https://www.langdock.com/pricing ### Admin approval Documented: There are the roles Member, Editor and Admin, plus up to 5 custom roles and extra permissions. Admins decide on the visibility of agents and, according to the governance page, can approve or block versions. Evidence: https://docs.langdock.com/en/admin/workspace/roles.md Evidence: https://docs.langdock.com/en/using-langdock/agents/introduction.md Evidence: https://www.langdock.com/products/governance ### Data access & team sharing Documented with conditions: OAuth connections act with the rights of the signed-in person by default. Through an agent with a preselected connection, others can run the action with those credentials. Application permissions can reach across the organisation; the documentation advises a clear need. Evidence: https://docs.langdock.com/en/using-langdock/integrations/connections.md ## Prices and included usage Pricing checked: 2026-11-05 Prices per seat per month excluding VAT; the tiers on the page start with the first 50 seats. The trial lasts 7 days, without a credit card and with EUR 5 of model credit. ### Core EUR 23.20 per standard seat, EUR 99.00 per Core Max seat Chat, agents, skills, integrations, SSO, SCIM and SAML, 2,500 workflow runs per month, 10 transcribed meetings per member. Governance until 1 January 2027 according to the page. Price source: https://www.langdock.com/pricing ### Work EUR 31.20 per standard seat, EUR 109.00 per Work Max seat Everything in Core, plus governance, unlimited meetings with a fair-use limit of 60 hours per week and 10,000 workflow runs per month. Price source: https://www.langdock.com/pricing ### Enterprise Custom, from 1,000 users Volume pricing, dedicated deployment possible, individual support. Price source: https://www.langdock.com/pricing ### Workflows Business Add-on: the page lists EUR 539 per workspace per month as well as EUR 449 for 40,000 and EUR 999 for 100,000 runs More workflow runs. Unused runs expire at the end of the billing period. Price source: https://www.langdock.com/pricing The page lists several amounts for Business side by side and does not explain how they relate. The home page mentions custom deployments from 1,000 seats, the security page from 2,000 and 5,000 seats. The API is billed separately by tokens. Third-party price information was not used. Pricing details: https://www.langdock.com/pricing ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Hosted operation by the provider; self-operation only from large seat numbers Sources reviewed: 2026-11-05 ### Files and working state Documented with conditions: Agents use up to 50 files, 5 library folders and 5 synced folders. According to the pricing page workflows keep data for 30 days in the Starter scope. The reviewed pages name no other periods; according to the security page data stays as long as needed for the service. Evidence: https://docs.langdock.com/en/using-langdock/agents/configuration.md Evidence: https://www.langdock.com/pricing Evidence: https://www.langdock.com/security ### Sign-ins Documented: Sign-in uses SAML SSO or, if allowed, a magic link for external people. Connections to tools use OAuth, an API key or a service account. Expired OAuth connections have to be reauthorised. Evidence: https://docs.langdock.com/en/admin/security/saml/saml.md Evidence: https://docs.langdock.com/en/using-langdock/integrations/connections.md ### Starting further runs Documented: Workflows start from a form, a schedule or an event in an app, once the version is published and active. Scheduled tasks run on a schedule and can use an agent. Evidence: https://docs.langdock.com/en/using-langdock/workflows/introduction.md Evidence: https://docs.langdock.com/en/using-langdock/workflows/fundamentals/core-concepts.md Evidence: https://docs.langdock.com/en/using-langdock/chat/scheduled.md ### Human intervention Documented: The "User input" node pauses the run and notifies recipients. MCP tools can be set to require confirmation per tool, but do not by default. The documentation names no deadline for waiting steps. Evidence: https://docs.langdock.com/en/using-langdock/workflows/fundamentals/human-in-the-loop.md Evidence: https://docs.langdock.com/en/using-langdock/guides/integrations/mcp/mcp.md ### Detecting errors Documented: After a run, nodes show input, output, messages, logs and usage. The product page mentions a run history with nodes and cost and the inspection of failed runs. Evidence: https://docs.langdock.com/en/using-langdock/workflows/fundamentals/core-concepts.md Evidence: https://www.langdock.com/products/workflows ### Resuming after failures Documented with conditions: Per node you choose stop, continue with the error as output, an error path or retry. Up to 5 retries are possible, but not for User input, Delay, Loop and triggers. The reviewed page does not describe resuming aborted runs. Evidence: https://docs.langdock.com/en/using-langdock/workflows/fundamentals/core-concepts.md ### Editorial assessment Langdock documents triggers, approvals and error options for workflows in concrete terms. The sub-processor list and general retention periods remain open. For MCP tools you should enable confirmations yourself. ## Memory and conversation continuity Scope: Chat memory for regular chats; agents use instructions and knowledge Sources accessed: 2026-11-05 Memory stores up to 50 facts and preferences in the account but does not apply in agent chats. Agents work with files and folders. ### Storage and scope Partly documented: According to the documentation memories are stored in the account, at most 50 at a time. The page does not name the physical storage system. - [Langdock Docs: Memory](https://docs.langdock.com/en/using-langdock/chat/tools/memory.md) ### Selection and timing Documented: The model recognises what is worth keeping, and you can explicitly ask it to save something. Very personal, short-lived and sensitive details are saved only on explicit request. - [Langdock Docs: Memory](https://docs.langdock.com/en/using-langdock/chat/tools/memory.md) ### Inspect, edit and delete Documented: In the Memory tab of the account settings you view, edit and delete entries. You can also do this by instruction in chat. - [Langdock Docs: Memory](https://docs.langdock.com/en/using-langdock/chat/tools/memory.md) ### Agent and channel boundaries Documented: Memory applies only in regular chats, not in project or agent chats. Workspace and personal settings must allow it, and the model must support tools. - [Langdock Docs: Memory](https://docs.langdock.com/en/using-langdock/chat/tools/memory.md) ### Retrieval Partly documented: Saved entries are available in later regular chats. The documentation does not say how retrieval works technically. Agent knowledge is retrieved as relevant excerpts. - [Langdock Docs: Memory](https://docs.langdock.com/en/using-langdock/chat/tools/memory.md) - [Langdock Docs: Agent configuration](https://docs.langdock.com/en/using-langdock/agents/configuration.md) ### Session reset and compaction Partly documented: According to the documentation chat history can be summarised over time. It does not describe resetting memory beyond deleting entries. - [Langdock Docs: Memory](https://docs.langdock.com/en/using-langdock/chat/tools/memory.md) ## Context A contract with Langdock and an active plan. The sub-processor list was not available when fetched; self-operation requires 5,000 seats according to the page. "GDPR compliant" is a claim by the provider. Official website, pricing page, security page, privacy policy and documentation reviewed. The Trust Center showed only its title when fetched. Feature descriptions come from the provider; example tasks are editorial. Our own hands-on tests are still pending. ## Open points Europe, availability still unclear: - Sub-processors and third countries - Certificates and "GDPR compliant" Requirements and limits, not yet confirmed: - Sub-processors not readable - Model region labels ## Sources - https://www.langdock.com/ - https://www.langdock.com/pricing - https://www.langdock.com/security - https://www.langdock.com/products/agents - https://www.langdock.com/products/workflows - https://www.langdock.com/products/integrations - https://www.langdock.com/products/governance - https://www.langdock.com/models - https://www.langdock.com/privacy-policy - https://trust.langdock.com/ - https://docs.langdock.com/en/using-langdock/agents/introduction.md - https://docs.langdock.com/en/using-langdock/agents/configuration.md - https://docs.langdock.com/en/using-langdock/workflows/introduction.md - https://docs.langdock.com/en/using-langdock/workflows/fundamentals/core-concepts.md - https://docs.langdock.com/en/using-langdock/workflows/fundamentals/human-in-the-loop.md - https://docs.langdock.com/en/using-langdock/chat/tools/memory.md - https://docs.langdock.com/en/using-langdock/guides/integrations/mcp/mcp.md - https://docs.langdock.com/en/using-langdock/integrations/connections.md - https://docs.langdock.com/en/admin/security/saml/saml.md - https://docs.langdock.com/en/admin/workspace/roles.md - https://docs.langdock.com/en/using-langdock/chat/scheduled.md - https://docs.langdock.com/en/admin/compliance-and-governance/legal-compliance.md - https://docs.langdock.com/en/admin/byok/byok.md ## Provider Langdock GmbH, based in Berlin, offers an AI platform for companies. - Operator: Langdock GmbH - Organization: Provider - Website: https://www.langdock.com - Reviewed: 2026-11-05 - Provider source: https://www.langdock.com/ - Provider source: https://www.langdock.com/privacy-policy [Sources and method](https://ki-agentenkompass.de/en/sources/)