AI AGENTS
Discord flagged-message moderation review with human sign-off
When a member reports a Discord message, an agent classifies the violation, drafts a moderation decision with rationale.
How it runs
The automated pipeline, trigger to output.
- TriggerMember reports a Discord messageDiscord
- ActionFetch message + surrounding channel contextDiscord
- ActionScore content with Hugging Face toxicity classifierHugging Face
- LogicDismiss low-confidence false alarms, escalate the rest
- ActionAgent drafts moderation decision + rationale
- OutputOpen private review thread for moderator sign-offDiscord
What it does
Turns ad-hoc Discord reports into structured, reviewable moderation decisions. An agent reads the flagged message and its surrounding context, classifies the likely rule violation, recommends an action (warn, mute, delete, no-action), and writes a plain-language rationale. Nothing is enforced automatically — the recommendation lands in a moderator-only thread for a human to sign off on.
When to use it
Use it when your server gets enough reports that moderators can't triage every one from scratch, but you still want a human making the final call. Ideal for communities with a written code of conduct where consistency and an audit trail matter.
How it works
- 1A Discord report (reaction flag or `/report` command) fires the trigger with the offending message ID.
- 2The agent pulls the message plus a few lines of channel context for tone and intent.
- 3A Hugging Face text-classification model scores the content for toxicity and harassment categories.
- 4Logic branches: clear false-alarms are auto-dismissed; anything above threshold proceeds.
- 5The agent drafts a decision card — violated rule, recommended action, confidence, and rationale.
- 6It opens a private Discord review thread tagging the on-call moderator for approve/override.
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.