Skip to main content

Docebo knowledge

  • Last updated:
  • Administrators

Introduction

Your organization's know-how doesn't only live in courses. It lives in internal documentation, wikis, shared drives, and files that your team relies on every day. Docebo Knowledge brings that content into the platform by connecting to the systems where it's stored, letting you curate it into Knowledge collections, and making it available to your users without duplicating or moving any files.

This expands what Docebo can do for your organization well beyond learning. By complementing your learning content with internal documentation and information, Docebo Knowledge helps users find answers and get support in their daily work, not just with training and development.

Because content is connected directly to its source system, it stays in sync automatically. There's no need to manually re-upload or update knowledge when something changes, and no need to separately manage who can see what: permissions from the source system are respected automatically.

Docebo Knowledge is activated by a Superadmin from the Knowledge card in the Launch pad.

Knowledge connectors

Once Docebo Knowledge is activated, you'll find Knowledge connectors under Add-ons and integrations. Setting up at least one connector is required before you can create a Knowledge collection, since collections are built from content pulled in through a connector.

A few things worth knowing before you set one up:

  • Setting up a connector usually requires support from your IT department, since it involves authorizing access to a source system.
  • There’s no cost or charge to set up or maintain a connector. 
  • Source system permissions are always enforced. Users only ever see what they already have access to in the connected system. The exact technical approach for this is dependent on what each source system provides in regards to retrieving permissions.

There are two types of connectors, which differ in how they make content available:

  • Indexing connectors sync the structure of the source system so you can browse it, and index the content you add to a collection. Indexed content is kept up to date automatically, so answers stay current without manual maintenance, and it counts toward your indexed data volume.
  • Live connectors don't index any content. When a user asks a question, Docebo searches the source system at that moment, using the user's own account and only within the channels or projects you've selected. Nothing is stored or indexed, so live connectors don't count toward your data volume.

For full details on connectors, including all the requirements and considerations, see Knowledge connectors. For step-by-step setup instructions for each system, see:

Knowledge collections

Once at least one Knowledge connector is set up, you're ready to create your first Knowledge collection. Collections are found under Content and delivery > Knowledge collections.

Knowledge collections are the central place for you to curate content from the connected systems to build a verified and trusted source of truth. It also allows you to organize your knowledge from different systems by topic, department, use case or whatever structure you need.

When creating a collection, you add content by browsing the connected systems through the file browser. As with source permissions for end users, each Superadmin only sees and can select the content they themselves have access to in the source system. What you select depends on the type of connector:

  • Indexing connectors: you select the files, pages, folders, or spaces you want to include. Their content is extracted and indexed when you add it to the collection.
  • Live connectors: you add a Project for Jira, a Channel for Slack or an Object for Salesforce. Nothing is copied. When a user later submits a prompt that searches the collection, content from the added projects and channels can be used as a source, searched at that moment with the user's own account.

Only adding content from indexing connectors counts toward your indexed data volume. Indexed data volume is billed according to your contract. For details about included volume and pricing, contact your Docebo representative or reach out to Docebo using your platform's Help center. Adding a Jira project, a Slack channel or a Salesforce object from a live connector never uses any data volume, because nothing is indexed.

A collection only becomes accessible to users once it's published. Publishing never overrides source system permissions: even after a collection is published, users will only be able to find and use the knowledge they're already entitled to access in the source system.

For a detailed look at building and managing collections, see Knowledge collections.

Using knowledge

Setting up and managing Docebo Knowledge, both connectors and collections, is only accessible to Superadmins. Users are only affected once at least one collection has been published, and even then, only within the limits of what they're permitted to access in the source system.

Published knowledge can surface for users in the following places:

  • AI assistant: When the AI assistant is activated, it can draw on content from published Knowledge collections to answer questions and respond to prompts. Knowledge used this way is cited alongside learning content, so users can verify the source, and clicking a citation takes them to the content in its source system. Users can also attach a Knowledge collection to a chat using the + button, to set that collection as preferred context for their prompt. For some connectors, the first time the AI assistant tries to retrieve information from a connected system, users are asked to connect their own account. This is a one-time step: the user approves access on the source system's own consent screen, and the assistant can then use that knowledge for them. Until a user has connected their account, content from that connector isn't included in their answers. This applies to live connectors, and to indexing connectors where access is checked with the user's own account.
  • AI tutor: If the AI tutor is activated, admins and power users can attach Knowledge collections to a course while editing it; the attached collection gives the Tutor extra context to answer learner questions that go beyond the course content itself.
  • Agents: Knowledge collections can be attached to agents to give them permanent access to relevant context. This supports two main use cases:
    • Agents built around workflows or tasks that depend on specific information being readily available.
    • Agents that act as subject matter experts. Attach a collection of verified, relevant knowledge, and the agent answers from that curated content instead of general knowledge. Learn more about agents.