AI AGENTS
Discord flagged-image vision triage with human review
When an image is reported in Discord, an agent runs it through a Hugging Face vision model for unsafe-content categories, drafts a removal recommendation with rationale.
How it runs
The automated pipeline, trigger to output.
- TriggerImage reported in DiscordDiscord
- ActionRun image through Hugging Face vision safety modelHugging Face
- LogicDismiss clearly safe images, escalate flagged ones
- ActionAgent drafts removal recommendation + rationale
- OutputPost to moderator review channel for sign-offDiscord
- ActionRemove approved image in Discord and log outcomeDiscord
What it does
Extends moderation review to images, which text classifiers miss. When a posted image is flagged, the agent runs it through a vision safety model, interprets the category scores, and drafts a recommendation — remove, allow, or escalate — with a rationale a moderator can verify. No image is deleted without human approval.
When to use it
Use it for servers where image and meme posting is heavy and rule-breaking visuals (NSFW, gore, hateful symbols) slip past text-only moderation. It gives moderators a pre-triaged recommendation instead of asking them to eyeball every reported image cold.
How it works
- 1A reported image in Discord fires the trigger with the attachment URL.
- 2The agent fetches the image and submits it to a Hugging Face vision safety model.
- 3Logic branches on the returned category scores: clearly safe images are dismissed; flagged ones continue.
- 4The agent drafts a removal recommendation citing the triggering categories and confidence.
- 5It posts the image, scores, and recommendation to a moderator review channel.
- 6On approval the agent removes the image in Discord and logs the outcome.
Set it up
What you configure once, before turning it on.
- 1Connect DiscordCommunity channels + voice + bots.
- 2Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI Agents workflows
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Weekly On-Call Doc-Gap Digest
Each week the agent reviews every Sentry issue resolved in the last 7 days, ranks the ones whose runbook coverage is missing or thin.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.