Anonymous means anonymous. No name, no email, no student ID, anywhere in the chain.
Students tell you the truth about a course only when they're certain it can't be traced back to them. This recipe collects no identifying field at any point, so there's nothing to trace. AI reads each submission, flags anything abusive or off-topic before staff ever see it, and tags sentiment and themes onto the row. When a rating is low or the sentiment turns negative, the department head is alerted in seconds: with the course, the instructor, and the comments, and nothing about who wrote them.
Free · no credit card · you connect your own apps
Installing provisions each one, wired together and ready to run.
A fully anonymous course and teaching-quality survey. Publishing it auto-creates the response sheet (the single system of record) which the workflow extends with moderation_flag, sentiment, and themes.
Fires on each new anonymous row. Moderates the free text, classifies sentiment and themes, saves the analysis back to the row, and alerts the department head when a rating is low, sentiment is negative, or the text is flagged.
You connect your own accounts. Swap any app that offers an alternative at install.
Alerts the department head when a rating is low, sentiment is negative, or the text is flagged, so teaching-quality issues get attention. Swap for Telegram, Discord, or Google Chat.
The student opens the Anonymous Course Feedback survey and rates the course, the teaching quality, and the workload, then adds free-text comments. No name, no email, no student ID is ever asked for, which is the entire point, and the reason the answers are worth reading. Publishing the form auto-creates its response sheet, so every submission is captured with no extra setup.
One TinyGPT step reads each submission and returns structured JSON: a moderation_flag of clean or flagged (abusive, harassing, or off-topic text gets caught here), a sentiment of positive, neutral, or negative, and themes: comma-separated tags naming what the comments are actually about, from teaching-clarity, workload, pacing, materials, assessment, engagement, support, and facilities.
The moderation flag, sentiment, and themes are written straight back onto the same anonymous row. No second sheet, no join key, and nothing added that could identify the student. What you end up with is a clean aggregate dataset you can actually use in a teaching-quality review.
When a rating falls at or below the threshold you set, when sentiment is negative, or when the text is flagged, the course, instructor, ratings, sentiment, themes, and improvement text are posted to the department head's Slack channel, with no student identity attached. Swap Slack for Telegram, Discord, or Google Chat at install.
Everything it creates is an ordinary form, table and workflow in your workspace. Edit any of it after install. Nothing is locked.
