# DeutschlandGPT German AI platform with chat, agent mode, Cowork and Code on the desktop as well as workflows, hosted according to the provider in the Open Telekom Cloud. Canonical profile: https://ki-agentenkompass.de/en/agents/deutschlandgpt/ 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 DeutschlandGPT is a proprietary product of DeutschlandGPT GmbH, which according to the trust page belongs to Titanom Group GmbH. The platform brings models from several providers into one interface. - Provider: DeutschlandGPT GmbH - Product family: DeutschlandGPT - Profile type: AI work platform with agent mode, desktop agents and workflows - Environment: Web, iOS and Android, desktop app for macOS, Windows and Linux, add-ins for Office and Chrome, platform API and chat widget - Connections: According to the page 87 tools and data sources, including Microsoft 365, Google Workspace, Confluence, Jira, Slack, HubSpot, Salesforce and GitHub - Setup: Create a free account and start in chat or the desktop app. For actions you connect integrations, usually by OAuth; administrators set rules and roles. - Pricing model: Free for EUR 0; Business EUR 24 per user per month, EUR 20 when paid annually, plus VAT; Enterprise on request. Workflows and API are billed additionally by usage. ## Key features ### Agent mode in chat For each message you set whether the AI only reads, researches the web or acts in your systems, such as sending emails or creating Jira tickets. Acting can be controlled per integration. Source: https://deutschlandgpt.de/plattform/chat ### Cowork in local folders You name a goal, Cowork plans the steps, shows the plan and works in shared folders. It creates Excel, Word, PDF and PowerPoint files. It runs as a desktop app for macOS, Windows and Linux. Source: https://deutschlandgpt.de/plattform/cowork ### Code for software tasks The coding agent searches a project, changes files, runs builds, tests and Git, and checks its result in a preview. You see every step. Source: https://deutschlandgpt.de/plattform/code ### Workflows with approval Triggers are manual, scheduled, webhook, form, integration or subworkflow. An approval switch on a node holds the run until a person decides. Source: https://docs.deutschlandgpt.de/workflows ### Special applications Custom assistants with behaviour, knowledge and tools that can also act according to the page. There are four sharing levels from private to editable across the organisation. The page's address calls them "agents". Source: https://deutschlandgpt.de/plattform/agenten ### Integrations The page lists 87 tools and data sources, the FAQ "over 80". The modes Search (read only) and Actions (read and write) can be released separately per tool. Source: https://deutschlandgpt.de/plattform/integrationen ### Roles and permissions According to the page, rights run through roles with over 90 individual permissions, with SAML SSO and SCIM from Business. Security-relevant actions are logged and can be exported. Source: https://deutschlandgpt.de/steuerung ## Example workflows ### Create a report from a folder - Your input: A shared folder with source files and a goal instead of individual steps. - Possible result: Cowork shows the plan and then creates a file in the folder. - What to check: Confirm each change in Normal mode and check the result in the change view. ### Ticket intake with approval - Your input: A workflow with an integration trigger, an AI step and an approval switch. - Possible result: The run holds at the node until a person approves or rejects. - What to check: Check status, duration and cost per node in the history and set a spending limit. ## Requirements and limits ### Auto mode without asking Limitation: In Auto mode actions run without asking. A review model checks risky commands, but deleting and overwriting need no confirmation. Completed actions are not reverted when you stop a run. Source: https://docs.deutschlandgpt.de/desktop/cowork ### No self-operation Limitation: The trust page rules out operation in your own data centre. Cowork and Code run locally on the device, the rest of the platform with the provider. Source: https://deutschlandgpt.de/trust ### Access to Cowork and Code through roles Requirement: Role permissions control access to Cowork and Code. Commands are available in Cowork only if your account may also use Code. Source: https://docs.deutschlandgpt.de/desktop ### Budget per plan Limitation: Each plan includes a monthly AI budget. Multi-step runs use more. After that you switch to pay-as-you-go or, on Business and Enterprise, to cheaper models. Source: https://deutschlandgpt.de/limits ### Audit log by plan Not yet confirmed: The governance page describes exportable logs, the pricing page lists the audit log under Enterprise. It is not clear from this what Business includes. Source: https://deutschlandgpt.de/preise ### Error paths in workflows Not yet confirmed: Failed nodes show their error in the history. The workflow documentation does not describe retries or error paths. Source: https://docs.deutschlandgpt.de/workflows ## A good fit if … - you want to use agent work on the desktop, in chat and in workflows from one account - you want to check sub-processors and model routes on public pages before signing - you want to start with a free account without a sales call ## Less suitable if … - you have to run the platform in your own data centre - you require a SOC 2 attestation or a completed security questionnaire from the provider - you need documented retries and error paths for workflows Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Fixed choice across providers You pick from a dropdown of around 50 language models from OpenAI, Anthropic, Google and Mistral, plus open models in the Open Telekom Cloud. The free plan includes only selected models, and the choice shrinks if your organization activates the §203 professional-secrecy feature. The pages checked do not mention your own keys or models. - Model families named: OpenAI (GPT), Anthropic (Claude), Google (Gemini), Mistral, Alibaba (Qwen), Nvidia (Nemotron), Z.ai (GLM) - Model choice: You choose - Your own API key: Not stated - Router or custom endpoint: Not stated - Local models: Not stated - Depends on: Plan, Admin approval Documented · Sources accessed on: 2026-11-05 - [DeutschlandGPT: Modelle](https://deutschlandgpt.de/modelle) - [DeutschlandGPT: FAQ](https://deutschlandgpt.de/faq) - [DeutschlandGPT: Preise](https://deutschlandgpt.de/preise) - [DeutschlandGPT Docs: Organisation](https://docs.deutschlandgpt.de/organization/general) ## Europe & regional availability Trust page, data processing annex, models page and FAQ reviewed. All statements come from the provider; certificates and contracts with model providers were not seen. The trust page dates one agreement after its own revision date. Reviewed scope: Platform with the provider in Germany; models through EU access Reviewed on: 2026-11-05 ### Storage in Germany Available According to the trust page history, files and settings are stored in the Open Telekom Cloud in Magdeburg and Biere, operated by T-Systems. The data processing terms state persistent data only in German data centres. According to those terms administrative access and support come from the EU. Region covered: Germany Documented reason: Provider statement in the trust page and data processing terms. The BSI C5 attestation belongs to T-Systems, not DeutschlandGPT. Official source: https://deutschlandgpt.de/trust Official source: https://deutschlandgpt.de/auftragsverarbeitung ### Model processing in the EU With requirements According to the trust page models run through EU access: OpenAI through Azure and OpenAI Ireland, Claude through AWS, Gemini through Google Vertex, plus Mistral. Open models run in the Open Telekom Cloud. For all model providers the provider cites agreed zero data retention and no training. Region covered: EU Documented reason: Contracts with model providers cannot be viewed. For US providers processing runs through EU subsidiaries according to the page. Official source: https://deutschlandgpt.de/trust Official source: https://deutschlandgpt.de/modelle Official source: https://deutschlandgpt.de/faq ### Data processing agreement and sub-processors Available The data processing agreement under Art. 28 GDPR is publicly readable. Annex IV lists T-Systems, Hetzner, IONOS, Microsoft Ireland, AWS EMEA, Google Cloud EMEA, Mistral AI, OpenAI Ireland, Linkup and Sentry. Region covered: EU/EEA Documented reason: The contract text itself documents the list. Official source: https://deutschlandgpt.de/auftragsverarbeitung ### "The data never leaves the EU" With requirements The FAQ and trust page say so. The data processing terms name as an exception the error monitoring by Sentry, based in the USA, without user content and in an EU data centre, based on standard contractual clauses. Region covered: EU and USA Documented reason: "Outside US jurisdiction" is a provider claim. The pages give no legal assessment. Official source: https://deutschlandgpt.de/faq Official source: https://deutschlandgpt.de/trust Official source: https://deutschlandgpt.de/auftragsverarbeitung Official source: https://deutschlandgpt.de/ ### Certificates and limits Availability still unclear According to the trust page ISO/IEC 27001:2022 and ISO 9001:2015 from TÜV SÜD are issued to the parent company Titanom Group GmbH, with DeutschlandGPT GmbH listed as a site. The page names no SOC 2 report. "GDPR compliant" remains a provider label. Region covered: EU/EEA Documented reason: Certificates not viewed ourselves; no authority assessment found. Official source: https://deutschlandgpt.de/trust ## 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 role management; Cowork and Code on the device Sources reviewed: 2026-11-05 ### Account used Documented: SAML SSO and SCIM are available from the Business plan. Organisations can require two-factor authentication. According to the documentation the desktop app stores tokens in the operating system's credential store. Evidence: https://deutschlandgpt.de/steuerung Evidence: https://docs.deutschlandgpt.de/security Evidence: https://docs.deutschlandgpt.de/desktop ### Admin approval Documented: Administrators enable integrations across the organisation and release Search and Actions separately per tool. Chat defaults govern agent mode, tool policies govern new integrations and local MCP servers. Evidence: https://deutschlandgpt.de/plattform/integrationen Evidence: https://docs.deutschlandgpt.de/organization/general ### Data access & team sharing Documented with conditions: According to the page integrations take over the access rights of the connected system. Cowork and Code work only in shared folders; protected locations such as .ssh or .aws stay blocked even there. According to the documentation the command check does not detect paths a program builds at runtime. Evidence: https://deutschlandgpt.de/plattform/integrationen Evidence: https://docs.deutschlandgpt.de/desktop/cowork ## Prices and included usage Pricing checked: 2026-11-05 Prices per user plus VAT. Free stays free of charge. Workflows, API and chat widget cost extra by usage. ### Free EUR 0 Limited usage, special applications and projects. Cowork, Code and integrations are included, but not meeting transcription, user administration and add-ins. Price source: https://deutschlandgpt.de/preise ### Business EUR 24 per user per month, EUR 20 annually Cowork, Code, meeting transcription, user administration, SAML SSO, SCIM and configurable deletion periods. Professional secrecy mode at no extra charge. Price source: https://deutschlandgpt.de/preise ### Business 5× The page lists EUR 100; it does not clearly state the billing period there Five times higher limits. Price source: https://deutschlandgpt.de/preise ### Enterprise Custom on request Everything in Business, plus dedicated onboarding, white labelling, payment by invoice, personal consulting, audit log and chat widget. Price source: https://deutschlandgpt.de/preise The FAQ says "from EUR 19", the plan page EUR 20 and EUR 24. Some pages mention a "Pro" plan that the plan overview does not list. The integrations page says all integrations are in every plan, but only one can be connected on the free plan. Third-party price information was not used. Pricing details: https://deutschlandgpt.de/preise ## 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: Platform with the provider; Cowork and Code as a desktop app on your device Sources reviewed: 2026-11-05 ### Files and working state Documented: Cowork works in a local folder that persists between sessions. Change history is kept for 30 days or up to 1 GB. For conversations you choose a period or "never"; according to the solutions page the platform does not delete automatically by default. Evidence: https://docs.deutschlandgpt.de/desktop/cowork Evidence: https://docs.deutschlandgpt.de/data-storage/general Evidence: https://www.deutschlandgpt.de/loesungen/datenschutz ### Sign-ins Documented: The desktop app signs in through the browser. In the organisation SAML SSO, SCIM and optionally enforced two-factor authentication apply. Most integrations use OAuth. Evidence: https://docs.deutschlandgpt.de/desktop Evidence: https://deutschlandgpt.de/steuerung Evidence: https://docs.deutschlandgpt.de/security Evidence: https://deutschlandgpt.de/plattform/integrationen ### Starting further runs Documented: Workflows start manually, on a schedule, by webhook, form, integration or as a subworkflow once a version is deployed. For Cowork the product page names no schedules and points to Workflows. A "Don't ask" mode is intended for unattended runs. Evidence: https://docs.deutschlandgpt.de/workflows Evidence: https://deutschlandgpt.de/plattform/cowork Evidence: https://docs.deutschlandgpt.de/desktop/cowork ### Human intervention Documented: In Normal mode Cowork asks before changes and commands, in Plan mode it changes nothing, in Auto mode it does not ask. In workflows an approval switch holds the run. In chat you control acting per integration. Evidence: https://docs.deutschlandgpt.de/desktop/cowork Evidence: https://docs.deutschlandgpt.de/workflows Evidence: https://deutschlandgpt.de/plattform/chat ### Detecting errors Documented: The workflow history shows status, duration, cost and the error per node. The desktop app marks sessions as waiting, running, failed or done. The page says nothing about how long workflow logs are kept. Evidence: https://docs.deutschlandgpt.de/workflows Evidence: https://docs.deutschlandgpt.de/desktop ### Resuming after failures Documented with conditions: If a Cowork run reaches its step budget, "Weiterarbeiten" (continue working) resumes the same run. Stopping ends it, and completed actions stay. For workflows the documentation describes no retry and no error path. Evidence: https://docs.deutschlandgpt.de/desktop/cowork Evidence: https://docs.deutschlandgpt.de/workflows ### Editorial assessment DeutschlandGPT discloses sub-processors, model routes and the rights of desktop agents and names concrete limits. Error paths in workflows are not documented. You should check the promise "outside US jurisdiction" against the data processing terms, because they also list EU companies of US providers and Sentry, based in the USA. ## Memory and conversation continuity Scope: Two profile fields and context per project; no dedicated memory feature documented Sources accessed: 2026-11-05 According to the documentation the AI remembers only two profile fields from one conversation to the next. Projects and folders provide lasting context. ### Storage and scope Documented: Two free-text fields under Settings, Profile, each up to 2,048 characters. According to the trust page the data is stored in the Open Telekom Cloud in Germany. - [DeutschlandGPT Docs: Benutzerkonto](https://docs.deutschlandgpt.de/account/general) - [DeutschlandGPT: Trust](https://deutschlandgpt.de/trust) ### Selection and timing Documented: You fill in the fields yourself and save them. The documentation does not describe automatic remembering. - [DeutschlandGPT Docs: Benutzerkonto](https://docs.deutschlandgpt.de/account/general) ### Inspect, edit and delete Partly documented: You edit or clear the fields in your profile. The page describes no admin view of them. - [DeutschlandGPT Docs: Benutzerkonto](https://docs.deutschlandgpt.de/account/general) ### Agent and channel boundaries Partly documented: The fields feed into every conversation. According to the FAQ the context of a client matter persists across its chats but does not move between matters. The documentation does not say whether the fields also apply in Cowork and Code. - [DeutschlandGPT Docs: Benutzerkonto](https://docs.deutschlandgpt.de/account/general) - [DeutschlandGPT: FAQ](https://deutschlandgpt.de/faq) ### Retrieval Partly documented: According to the documentation the profile fields are included in every conversation. The reviewed page does not say how project context is selected. - [DeutschlandGPT Docs: Benutzerkonto](https://docs.deutschlandgpt.de/account/general) ### Session reset and compaction Partly documented: The reviewed pages say nothing about compaction. Subagent transcripts survive restarts and are deleted after 30 days or with the conversation. - [DeutschlandGPT Docs: Cowork](https://docs.deutschlandgpt.de/desktop/cowork) ## Context An account and, for central administration, the Business plan. "GDPR compliant" and "outside US jurisdiction" are provider claims. According to the trust page the ISO certificates are held by the parent company and the BSI C5 attestation by the host T-Systems. Official website, pricing page, trust page, data processing terms and documentation reviewed. Feature descriptions and security statements come from the provider, and we did not view the certificates ourselves; example tasks are editorial. Our own hands-on tests are still pending. ## Open points Europe, availability still unclear: - Certificates and limits Requirements and limits, not yet confirmed: - Audit log by plan - Error paths in workflows ## Sources - https://deutschlandgpt.de/ - https://deutschlandgpt.de/preise - https://deutschlandgpt.de/plattform/agenten - https://deutschlandgpt.de/plattform/workflows - https://deutschlandgpt.de/plattform/chat - https://deutschlandgpt.de/plattform/cowork - https://deutschlandgpt.de/plattform/code - https://deutschlandgpt.de/plattform/integrationen - https://deutschlandgpt.de/steuerung - https://deutschlandgpt.de/trust - https://deutschlandgpt.de/auftragsverarbeitung - https://deutschlandgpt.de/limits - https://deutschlandgpt.de/modelle - https://deutschlandgpt.de/faq - https://deutschlandgpt.de/datenschutzhinweise - https://www.deutschlandgpt.de/loesungen/datenschutz - https://docs.deutschlandgpt.de/workflows - https://docs.deutschlandgpt.de/organization/general - https://docs.deutschlandgpt.de/desktop - https://docs.deutschlandgpt.de/desktop/cowork - https://docs.deutschlandgpt.de/data-storage/general - https://docs.deutschlandgpt.de/account/general - https://docs.deutschlandgpt.de/security ## Provider DeutschlandGPT GmbH offers an AI platform for organisations. According to the trust page its parent company is Titanom Group GmbH. - Operator: DeutschlandGPT GmbH - Organization: Provider - Website: https://www.deutschlandgpt.de - Reviewed: 2026-11-05 - Provider source: https://deutschlandgpt.de/ - Provider source: https://deutschlandgpt.de/trust [Sources and method](https://ki-agentenkompass.de/en/sources/)