# Docebo Agents Specialist agents for training and onboarding: create courses, support learners and automate learning administration. Requires Docebo Learn. Canonical profile: https://ki-agentenkompass.de/en/agents/docebo-agents/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-11-02 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview A combined suite within Docebo Learn, available since 28 October 2026. Primarily suited to organizational learning teams. - Provider: Docebo - Product family: Docebo - Profile type: Agent suite for training - Environment: Docebo Learn cloud platform - Connections: Docebo Creator, learner profiles and connected enterprise systems - Setup: Requires Docebo Learn, administrator setup and approved content and actions. - Pricing model: Custom platform quote; Docebo Agents consumes AI Credits. Public unit prices are unavailable. ## Key features ### Courses from source material Authoring Agent generates structured courses with interactive elements and assessments. Source: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx ### In-course learning support Tutor Agent answers questions using course content and approved knowledge. Source: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx ### Reinforce learning Reinforcement Agent provides personalized, spaced practice. Source: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx ### Select course offerings Marketplace Agent compares content and imports selected courses. Source: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx ### Custom workflows with AgentHub Administrators configure goals, actions, permissions and human approvals without code. Source: https://www.docebo.com/products/agents/ ## Example workflows ### Prepare an onboarding course - Your input: Create an introductory course with knowledge checks from our approved documents. - Possible result: A course draft for subject-matter approval. - What to check: Check accuracy, freshness and access permissions. ### Compile learning options - Your input: Compare suitable courses for training our service team. - Possible result: A selection for review and subsequent import. - What to check: Check licensing costs, language, learning goals and audience before importing. ## Requirements and limits ### Docebo Learn required Requirement: Requires Docebo Learn, administrator setup and approved content and actions. Source: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx ### Contract and AI Credits Limitation: Custom platform quote; Docebo Agents consumes AI Credits. Public unit prices are unavailable. Source: https://www.docebo.com/pricing/ ### Value in your learning operation Not yet confirmed: The suite requires the learning platform. Time-saving claims are provider reports; effort and value in your own learning operation require assessment. Source: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx ## A good fit if … - your company already uses Docebo Learn and wants to use agents there - administrators should decide which actions need human approval - course outlines, assessments or learning plans should be created from existing documents and knowledge sources ## Less suitable if … - you want a tool without a learning platform and without AI credit consumption - you need public per-item prices, as the pricing page lists none Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Models not stated The agents product page names no models. The sub-processor list shows AWS Bedrock, Vertex AI and Azure OpenAI for Docebo AI features, but these are hosts and are not tied to the agents. The checked pages do not cover model choice or own keys. - Model families named: None named - Model choice: Not stated - Your own API key: Not stated - Router or custom endpoint: Not stated - Local models: Not stated Partly documented · Sources accessed on: 2026-11-05 - [Docebo: Agents](https://www.docebo.com/products/agents/) - [Docebo: Sub-processors list](https://tos.docebo.com/Docebo-sub-processors-list.pdf) ## Europe & regional availability Announced for Learn customers; sources state no EU-wide exclusion. Confirm the specific Agents data processing contractually. Reviewed scope: Access and data processing in Germany and the EU Reviewed on: 2026-11-02 ### With a Learn contract and data review With requirements The subprocessor list names EU regions for certain services and AI features. Dated January 2026, it provides limited confirmation of data flows for the newly launched Agents suite. Region covered: Germany / EU Documented reason: Contract and configuration conditions; reviewed sources do not establish a specific restriction caused by the AI Act, DMA or GDPR. Official source: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx Official source: https://tos.docebo.com/Docebo-sub-processors-list.pdf ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Docebo Agents within a company's Docebo Learn platform Sources reviewed: 2026-11-05 ### Account used Open in reviewed sources: The reviewed pages do not say which account the agents act with. They only state that agents respect the permissions of connected source systems and everyone sees only what they are allowed to see. Evidence: https://www.docebo.com/products/agents/ Evidence: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx ### Admin approval Documented: Administrators decide which agents run and who may use them, and which actions need human approval beforehand. They can see and manage AI credit usage; in the plan they set access and limits. Evidence: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx Evidence: https://www.docebo.com/pricing/ ### Data access & team sharing Documented: According to the product page, agents use Docebo learning data, skills profiles and uploaded knowledge as well as connected sources such as Google Drive, SharePoint, Confluence, Slack and Salesforce. The announcement names SharePoint, Confluence, Google Drive and Slack as approved sources; knowledge inherits the permissions of each source. Evidence: https://www.docebo.com/products/agents/ Evidence: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx ## Prices and included usage Pricing checked: 2026-11-02 Custom platform quote; Docebo Agents consumes AI Credits. Public unit prices are unavailable. The pricing page lists AI Credits as an add-on for Elevate and Enterprise. Confirm allowance and consumption in the quote. Pricing details: https://www.docebo.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 platform, agents configured through AgentHub Sources reviewed: 2026-11-05 ### Files and working state Open in reviewed sources: The reviewed pages do not describe what working state agents keep between runs. The announcement explicitly does not cover retention or data residency. Evidence: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx ### Sign-ins Open in reviewed sources: Validity and expiry of connections to source systems are not described in the reviewed sources. Evidence: https://www.docebo.com/products/agents/ ### Starting further runs Documented: In the no-code builder AgentHub you choose whether an agent runs on a schedule or when conditions change. Agents can monitor conditions, run multi-step workflows, send reminders and generate reports. Evidence: https://www.docebo.com/products/agents/ ### Human intervention Documented: According to the announcement, administrators decide which actions need human approval before they happen. The product page also mentions escalation rules and gradually expandable autonomy. Evidence: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx Evidence: https://www.docebo.com/products/agents/ ### Detecting errors Documented with conditions: The product page promises audit-ready activity logs with traceable agent actions; the announcement mentions a log for IT, security and compliance. The pages do not describe how failures are shown or reported. Evidence: https://www.docebo.com/products/agents/ Evidence: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx ### Resuming after failures Open in reviewed sources: Resuming or retrying after failures is not described in the reviewed sources. Evidence: https://www.docebo.com/products/agents/ ### Editorial assessment Control through approvals, permissions and logs sits with the platform's administrators. Error handling and recovery are not documented and should be clarified with Docebo before use. ## Memory and conversation continuity Scope: Docebo Learn with Agents, October 2026 launch offering Sources accessed: 2026-11-04 Learner profiles and earlier practice answers provide context; general memory remains unspecified. ### Storage and scope Partly documented: Agents use learning history, skills profiles, courses and company knowledge. A separate general store for learned conversation facts is not specified. - [Docebo Agents](https://www.docebo.com/products/agents/) - [Launch of Knowledge and Agents](https://www.docebo.com/company/newsroom/docebo-expands-workforce-readiness-platform-with-launch-of-knowledge-and-agents/) ### Selection and timing Partly documented: The Reinforcement Agent builds practice on earlier answers. Selection and storage of broader conversation memories are not explained. - [Docebo Agents](https://www.docebo.com/products/agents/) - [Launch of Knowledge and Agents](https://www.docebo.com/company/newsroom/docebo-expands-workforce-readiness-platform-with-launch-of-knowledge-and-agents/) ### Inspect, edit and delete Not publicly established: Custom agents' instructions and permitted actions are configurable. A separate memory view with fact editing and deletion is not described. - [Docebo Agents](https://www.docebo.com/products/agents/) - [Launch of Knowledge and Agents](https://www.docebo.com/company/newsroom/docebo-expands-workforce-readiness-platform-with-launch-of-knowledge-and-agents/) ### Agent and channel boundaries Partly documented: Context concerns learners, courses and authorized company knowledge. Isolation of durable memories between agents or channels remains unspecified. - [Docebo Agents](https://www.docebo.com/products/agents/) - [Launch of Knowledge and Agents](https://www.docebo.com/company/newsroom/docebo-expands-workforce-readiness-platform-with-launch-of-knowledge-and-agents/) ### Retrieval Partly documented: Tutor answers draw on course material and approved knowledge; reinforcement uses earlier answers. This establishes domain context, not a general memory search index. - [Docebo Agents](https://www.docebo.com/products/agents/) - [Launch of Knowledge and Agents](https://www.docebo.com/company/newsroom/docebo-expands-workforce-readiness-platform-with-launch-of-knowledge-and-agents/) ### Session reset and compaction Partly documented: Practice continuity after a course ends is described. Specific chat reset, compaction and long-term memory retention rules are not published. - [Docebo Agents](https://www.docebo.com/products/agents/) - [Launch of Knowledge and Agents](https://www.docebo.com/company/newsroom/docebo-expands-workforce-readiness-platform-with-launch-of-knowledge-and-agents/) ## Context The suite requires the learning platform. Time-saving claims are provider reports; effort and value in your own learning operation require assessment. Provider sources reviewed; over 50 pilot customers according to Docebo. Sources document the offering; no hands-on testing conducted. Example tasks are editorial. ## Open points Requirements and limits, not yet confirmed: - Value in your learning operation ## Sources - https://www.docebo.com/products/agents/ - https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx - https://www.docebo.com/pricing/ - https://tos.docebo.com/Docebo-sub-processors-list.pdf ## Provider Publicly listed provider of an enterprise learning and training platform. - Operator: Docebo Inc. - Organization: Provider - Website: https://www.docebo.com/products/agents/ - Reviewed: 2026-11-02 - Provider source: https://www.docebo.inc/news/news-details/2026/Docebo-Expands-Workforce-Readiness-Platform-with-Launch-of-Knowledge-and-Agents/default.aspx [Sources and method](https://ki-agentenkompass.de/en/sources/)