AI AGENTS
Auto-suspend repeat offenders who keep submitting blocked prompts
On each blocked prompt, this workflow counts a user's recent violations in Postgres and, once they cross a strike threshold, suspends their generation access and alerts the team.
How it runs
The automated pipeline, trigger to output.
- TriggerBlocked-prompt event arrives via webhookHTTP webhook
- ActionCount user's recent blocks in PostgresPostgres
- LogicBranch on strike count vs threshold
- ActionSet user status to suspended in PostgresPostgres
- OutputAlert trust-and-safety in SlackSlack
What it does
This workflow enforces consequences for repeated abuse. Every time the moderation gate blocks a prompt, it tallies that user's violations over a rolling window. When someone exceeds the strike limit, their access flag is flipped to suspended in Postgres so future requests are rejected outright, and the team is notified.
When to use it
Use it alongside a prompt-moderation gate when a small number of users generate most of the abuse and you want automatic, auditable enforcement rather than manual bans.
How it works
- 1A webhook fires whenever the gate records a blocked prompt, carrying the user ID.
- 2A Postgres query counts that user's blocks within the rolling window.
- 3A logic branch checks the count against the strike threshold.
- 4If exceeded, a Postgres update sets the user's status to suspended.
- 5A Slack alert notifies the trust-and-safety team with the user and violation history.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 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
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.
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.
Datadog Bill Spike Attribution Agent
When a daily Datadog cost check detects a spend jump, an agent attributes the increase to the specific services and metric types driving it and posts a ranked breakdown to Slack.
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.
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.
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.
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.