Packback Discussion Bot — AI Posts & Replies

What it handles

Packback, done for you.

Written to read human

Posts are reconstructed as a person thinking, not rephrased from a template — varied sentence length, contractions, first-person voice, and the AI signature phrases stripped out.

Humanizer on by default

Every question and reply passes through a humanizer tuned against GPTZero and Turnitin's August 2025 anti-bypasser model, with a statistical pass that disrupts the uniform cadence those detectors flag.

Curiosity-score aware

It reads the minimum curiosity score out of the instructor's prompt and writes to clear it with room to spare, aiming roughly fifteen points above the required minimum.

Real replies to classmates

It reads the live discussion feed, skips anything you posted this run, and replies to genuine classmate posts — favoring the ones with the fewest existing replies.

On-topic, on-prompt

Questions and replies are generated against the professor's actual prompt and your course context, so they stay substantive and aligned instead of generic filler.

Your voice, if you want it

Add a few writing samples and Silent Student builds a style profile, so posts match how you already write across the course rather than reading like a stranger.

How it works

From open tab to submitted.

1

Point it at the assignment

Silent Student launches Packback through Canvas, confirms the LTI handoff, and reads the discussion requirements — the question count, reply count, and any minimum curiosity score.
2

It writes and humanizes

It drafts the question and replies on the prompt, then runs each through the humanizer before anything is posted. You can review every draft in the dashboard or skip straight to posting.
3

It posts and replies

It submits your question, reads the live feed, and replies to real classmate posts one at a time, retrying or skipping a form error without losing the whole assignment.
4

You get your time back

The run finishes on its own and logs what it posted. The weekly discussion stops being a thing you dread and becomes something that just happens quietly.

Questions

Packback FAQ

Posts are written to read human from the start and then run through a humanizer tuned against GPTZero and Turnitin's current anti-bypasser model, targeting the perplexity, burstiness, and cadence signals detectors look for. No tool can promise a specific detector outcome, and we don't — but this is built around the real research, not synonym-swapping.

Both. It reads the live discussion feed, filters out anything it posted this run, and replies to genuine classmate posts. It prefers posts with fewer existing replies so your participation isn't all piled onto the same popular thread.

It parses the minimum curiosity score out of the instructor's prompt and aims to clear it, targeting roughly fifteen points above the required minimum. Packback assigns the actual score, so this is what it writes toward, not a guaranteed number. The scoring logic runs server-side so it stays consistent across runs.

Yes. Add a few of your own writing samples and Silent Student builds a style profile it applies to your posts, so they match the voice you've used elsewhere in the course instead of reading like someone else wrote them.

Your choice. You can review every draft in the dashboard before anything goes live, or let it post and reply on its own once you trust it. Either way you get a log of exactly what it posted.

More integrations