Recheck graded work and update scores in Brightspace

A professor used an agent to regrade TA-marked assignments, compare answers with Claude, and revise grades and comments in Brightspace.

Done with Claude Code· Advanced· Oct 2026

What they did
The professor handed over assignment submissions that had already been graded by a TA. The agent reviewed each one again, looked for mistakes the TA had missed, and checked AI-written answers against Claude before making edits. It then updated the grades and feedback directly in Brightspace, while the professor only started the process.
How it went
The revisions added fuller feedback and changed scores where needed, including issues that had been overlooked before. After seeing the agent’s checks, the professor felt much more confident in the results.
Tips
Have the agent list every proposed grade change before it writes anything back to your course system. Keep a human review step before any final submission or overwrite.

Try it yourself with Claude Code

Review the submissions in [folder/export] for [course], using [rubric] and [answer key]. Regrade each one, check any AI-generated answers against [source/model], and prepare a table showing each score change, the reason, and suggested feedback. Pause and ask for my approval before you change any grades or feedback in [Brightspace/LMS], and do not submit, overwrite, or finalize anything until I confirm.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on x.com ↗

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.