AI AGENTS
High-severity Discord violations escalated to Slack on-call
When a Discord message scores as high-severity (threats, doxxing, CSAM signals), an agent immediately drafts an urgent decision and pages the trust-and-safety on-call in Slack…
How it runs
The automated pipeline, trigger to output.
- TriggerNew Discord message or report receivedDiscord
- ActionScore severity with Hugging Face classifierHugging Face
- LogicGate to high-confidence, high-severity only
- ActionAgent drafts urgent decision + rationale
- OutputPage trust-and-safety on-call in SlackSlack
- ActionApply approved action back in DiscordDiscord
What it does
Fast-paths only the dangerous stuff. Routine reports stay in your normal queue; this workflow fires when a message trips a high-severity threshold and needs a human within minutes. The agent drafts a recommended emergency action with rationale and pushes it to a Slack on-call channel where trust-and-safety can act instantly.
When to use it
Use it for the cases where delay is harmful — credible threats, doxxing, coordinated harassment, or illegal-content signals. Pair it with your regular review workflow so low-severity reports don't page anyone, and these never wait in a backlog.
How it works
- 1A new Discord message or report fires the trigger.
- 2A Hugging Face model scores the content across severe-harm categories.
- 3Logic gates hard: only high-confidence high-severity hits continue; everything else exits silently.
- 4The agent drafts an urgent decision — recommended action, affected users, and rationale.
- 5It posts an alert to the Slack trust-and-safety on-call channel with approve and override actions.
- 6On approval the agent applies the action back in Discord and timestamps the resolution.
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.
- 3Connect SlackChannels, DMs, threads, mentions.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, 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.