Learning Path knowledge
A Learning Path can carry its own reference material. The AI Fellow that runs the sessions reads this material and draws on it during the conversation, without the user seeing the files. Use it to give the Fellow the source documents behind a program: a policy, a product brief, a set of guidelines, or a short recording that frames the topic.
There are two scopes, both managed from the Learning Path editor:
- Path knowledge applies to every session in the Learning Path. Up to 3 files.
- Session knowledge applies only to the session it is attached to. Up to 2 files per session.
Path knowledge is available to the AI Fellow in every session. Session knowledge is available only while the user is in that specific session.

How it differs from an AI Fellow Knowledge Base
The AI Fellow Knowledge Base belongs to a standalone AI Fellow and travels with it wherever that AI Fellow is used. Learning Path knowledge belongs to the Learning Path itself and only shapes the sessions in that path. A Learning Path runs on its own AI Fellow, so the two do not overlap: use path or session knowledge for material specific to a program, and an AI Fellow Knowledge Base for a reusable reference AI Fellow.
Supported file formats
- Word (
.docx,.doc) - PowerPoint (
.pptx,.ppt) - Plain text (
.txt) - Markdown (
.md) - Audio (
.mp3,.wav,.m4a), automatically transcribed - Video (
.mp4,.mov,.webm), automatically transcribed
Add path knowledge
Add session knowledge

Remove a file at any time with the delete control next to it. The AI Fellow stops using the material once the change is processed.
Frontierz summarizes each file before the AI Fellow uses it, so keep files focused on the material that matters for the program. Short documents are kept in full; longer ones are condensed to their key points. For a non-sequential reference library, an AI Fellow Knowledge Base is a better fit.