In-course assistant for Skilljar + Rise
A floating in-course assistant trained on your own course data, right inside Rise courses in Skilljar.
Public AI and online search won’t help much when learners are training on internal workflows or unreleased features in an e-learning course.
In B2B/internal training, the answers people need are usually behind a login or not public yet. So when someone gets stuck mid-course, “go Google it” isn't any help, and a public LLM won’t have your course context.
This afternoon I built a floating in-course assistant in Claude Code so learners can chat directly with an LLM trained on your own course data to get context-aware answers right inside your Rise courses in Skilljar by Gainsight.
High-level configuration:
- Select your LLM and enter your API key (Claude, GPT, Gemini).
- Upload your course materials (lesson text, videos, transcripts, PDFs).
- Set up the widget (title, theme, placement, behavior, guardrails).
- Add a single JavaScript snippet to the header of your Skilljar theme.
- Scope it to the right e-learning courses (course ID, tag, or URL pattern).
Free and open-source: kelly-vibe-coding/in-course-assistant.