Canvas: Discussion Summary

Tags canvas AI

What is Discussion Summary?

Discussion Summary is an AI-enhanced course feature option that auto‑generates a custom summary of posts submitted to a Canvas Discussion. The feature is built on an AI large language model designed to identify patterns from the latest contributions to discussion threads. Prompts may be customized to focus the summary output, which is only visible to the instructor. As with most LLM tools summary output may not be accurate.

As an Instructor, why should I activate Discussion Summary?

Discussion Summary is a narrowly focused AI-enhanced tool in Canvas. If Discussions are not a common feature in a course, then it would not be useful. For instructors teaching large classes with Canvas Discussion activities, the course feature could be a useful way to explore patterns in student contributions, such as:

  • Condense long discussion threads into a set of highlights, new questions, or takeaways.

  • Analyze rhetoric and language patterns to provide formative feedback to the class.

  • Jump‑start next steps (polls, follow‑up prompts, reflections) by pointing to common themes.

How is the Discussion Summary course feature turned on in a Course?

Discussion Summary is turned off by default. Course Feature Options can be discovered by clicking on the Settings link at the bottom of the course-level Navigation menu, then clicking on the Feature Options tab. Click the red circled X under State next to Discussion Summary to turn it on.

What are some Best Practices for Instructors?

  1. Use or Request access to an Archive Canvas site to explore. Verify accuracy and watch for hallucinations before enabling in live courses. See how to request and Archive copy of a Canvas site under Hosted Archive Copy of a Canvas Site in Canvas: Sharing Site Content as an Archive or an ePub.

  2. Review Output. Treat any AI output from the Discussion Summary tool like a draft, not a final product. Large Language Model (LLM) outputs are not always accurate or reliable.

  3. Keep prompts focused. Clear, specific discussion questions yield clearer summaries. In testing, the AI summary output was often overly general to be helpful on its own. Instructors should test out alternative prompts that could return output with more specificity. Here are some alternative prompt suggestions:

    • Summarize the main themes related to [topic] and their frequency.

    • What concepts generated student confusion or misconceptions?

    • What questions did students most commonly ask?

    • Summarize points of disagreement or differing views.

    • Highlight examples of student interaction (replies, building on ideas).

    • Identify potential gaps in the discussion coverage of [topic].

    • What information might have been helpful before the discussion?

    • Note connections made to real-world examples or other course material.

    • Describe the types of evidence or support used by students.
       

  4. Check for PII. Remove or anonymize personal details that may have surfaced in the output before sharing.

  5. Turn off if needed. If your pedagogy relies on detailed, iterative discussions, you can disable the feature in Settings → Feature Options per course.

 

How does Discussion Summary Work in Canvas?

STEP

BEHIND THE SCENES

1. Click Summarize.

Only people with the Teacher role can see the button.

2. Data sent to AI.

The full prompt and all replies (including any personally identifiable information) are transmitted to the AI model for single‑use processing.

3. Summary output returned.

Canvas saves the text in its database; no data stays with the model.

4. Instructor review.

Able to edit or regenerate before choosing to share with students.

Privacy & Data Facts

  • Course content or submissions are used to train the AI model. The model is pre‑trained; it does not learn from your data.

  • PII exposure. Names or personal details in discussion posts are visible to the model during processing.
         Recommendation: remind students to keep sensitive info out of discussions.

  • Storage location. Summaries live in the Canvas database; Instructure does not send them back to the model.

What are known Limitations or Things to Watch for?

ISSUE

WHAT WE KNOW

OUTSTANDING QUESTION

Embedded media

Images, video, and audio posts are ignored.

Will alt‑text or transcripts be included later?

Can I regenerate a summary? 

Yes—click Regenerate and review the new draft.

Will students see my edits? 

Only after you click Post Summary. Until then, the text is private to you.

Multilingual support? 

The model handles many languages, but accuracy may vary.

How to get additional help?

For more information visit Canvas’ Nutrition Facts for Discussion Summaries page.

For technical support, contact Instructure Support by 24/7 phone [+1-833-890-4166] or email support@instructure.com. For pedagogical support schedule a consultation with a DLINQ team member.

 
 
Print Article