AI AGENTS
Discord Flagged-Message Triage Agent
When a community member reports a Discord message, an agent classifies the severity, logs the case to Postgres.
How it runs
The automated pipeline, trigger to output.
- TriggerDiscord report submitted for a messageDiscord
- ActionFetch flagged message + surrounding contextDiscord
- ActionAgent classifies severity and category
- ActionLog case to Postgres mod_cases tablePostgres
- LogicBranch on verdict: clean vs. violation
- OutputPost draft warning to private mod channelDiscord
What it does
Turns raw Discord reports into triaged moderation cases. An agent reads the reported message in context, classifies it (spam, harassment, off-topic, or clean), records the verdict in your case database, and routes only the real violations to humans with a pre-written warning ready to send.
When to use it
When your mod team is drowning in `/report` submissions and most of them are noise. Use this to auto-dismiss false alarms, keep an auditable record of every report, and hand moderators a short queue of pre-classified cases instead of a firehose.
How it works
- 1A Discord report event fires with the flagged message ID and reporter.
- 2The agent fetches the message plus a few surrounding messages for context from Discord.
- 3It classifies severity and writes the case (message, author, verdict, confidence) to a Postgres `mod_cases` table.
- 4A branch checks the verdict: clean or low-confidence reports are silently closed.
- 5For real violations, the agent drafts a tone-matched warning and posts it to a private mod review channel for one-click approval.
Set it up
What you configure once, before turning it on.
- 1Connect DiscordCommunity channels + voice + bots.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 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.