# Triage Hugging Face discussions on your models and datasets

> Every weekday morning, sort the questions and bug reports people post on your Hugging Face models into one Slack digest, with real bugs filed automatically.

- Workflow type: agent
- Services: Hugging Face, Linear, Slack Bot
- Categories: Engineering, Customer Support
- Published: 2026-08-14

## What it does

- Checks every model and dataset your organization publishes on Hugging Face and picks up whatever people posted overnight.
- Sorts each thread into a bug report, a feature request, a usage question, a licensing question, or spam, and ignores the automated bot pull requests that clutter the list.
- Files an issue in Linear for every genuine bug, including which model or dataset it came from, a link to the thread, and the reporter's setup details.
- Posts one Slack digest grouped by type, leading with the questions nobody has answered yet and flagging anything that has been waiting more than two days.

## What you'll need

- A Hugging Face account that publishes models or datasets under an organization, plus the organization name
- A Slack workspace with a channel your ML team watches
- A Linear workspace with a team to file bug reports into

## Prompt

Every weekday at 9am, sweep the discussions and pull requests on every model and dataset my organization publishes on Hugging Face, and triage whatever came in since the last run.

Start by enumerating our repos. Use Hugging Face List Models and List Datasets, both filtered with the author set to my organization name. These list endpoints are cursor paginated, so follow the pagination all the way through instead of stopping at the first page, otherwise repos get missed once we publish more than one page worth.

For each repo, call List Discussions. Repo ids are namespace/name, and repo scoped paths split them into separate namespace and repo segments, so handle that when building each call. This single endpoint returns both discussions and pull requests, so keep track of which is which. Skip automated bot pull requests such as model card updates, config bumps, and similar housekeeping opened by bot accounts, because those are high volume and would drown out the real threads.

For anything opened or updated since the last run, call Get Discussion to read the full thread along with its events. Monday's run should cover the whole weekend, not just Sunday.

Classify each thread as one of these: a bug report, a feature or model request, a usage question, a licensing or access question, or spam.

For genuine bug reports, create a Linear issue with Create Issue. Each issue should include the repo name, a link back to the discussion, the reporter's environment details if they gave any, and a short summary of what they hit. Do not open a second issue for a discussion that already produced one on an earlier run.

Then post a single digest to our ML team channel with Slack Bot Send a Message. One message, not one per repo. Group the threads by category, lead with the unanswered usage questions since those are the ones that cost us goodwill, and flag anything that has been sitting without a reply for more than 48 hours. If nothing new came in, post one short line saying so rather than an empty digest.

Finally, for stale usage questions only, meaning the ones with no reply for over 48 hours, leave a short acknowledgment on the thread with Comment on Discussion so the community knows we saw it. Never auto reply to bug reports or to licensing and access questions, because those need a human.

## How to customize

- Change the schedule, for example twice a day during a launch week or Mondays only
- Move the "waiting too long" line from 48 hours to whatever response time your team promises
- Decide which categories get an automatic acknowledgment, or switch auto replies off completely
- Send bugs to a specific Linear team, or set a priority based on how many people are hitting the issue

## FAQ

### Will it reply to people on my behalf?

Only in one narrow case: a usage question that has been sitting with no reply for more than 48 hours gets a short acknowledgment so the person knows you saw it. Bug reports and licensing or access questions are never answered automatically, because those need a real person.

### Does this cover datasets, or just models?

Both. It looks at every model and every dataset published under your organization, so a question left on a dataset card gets triaged the same way as one left on a model.

### What about all the automated pull requests bots open on my models?

They get skipped. Things like model card updates and config bumps are high volume and would bury the real threads, so they never reach the digest or your issue tracker.

### Do I have to use Linear?

No. Linear is what files the bug reports, but you can point that step at a different tracker, or remove it entirely and keep just the Slack digest.

### Will the same thread show up in the digest every morning?

No. Each run only looks at threads opened or updated since the last one, and it will not file a second issue for a bug it has already logged.

Use this prompt in General Input: https://www.generalinput.com/prompts/triage-hugging-face-discussions-on-your-models-and-datasets