AI AGENTS
Pre-screen Replicate image prompts at the API gate
Intercepts inbound image-generation requests over a webhook, classifies each prompt against your content policy.
How it runs
The automated pipeline, trigger to output.
- TriggerGeneration request arrives via webhookHTTP webhook
- ActionClassify prompt against policy categoriesOpenAI
- LogicBranch on whether any category exceeds threshold
- ActionDispatch clean prompt to ReplicateReplicate
- ActionLog verdict, scores, and prompt to PostgresPostgres
- OutputReturn prediction ID or rejection to callerHTTP webhook
What it does
This workflow sits in front of your Replicate image pipeline as a moderation gate. Every prompt your app submits is classified for policy violations (sexual, violent, hateful, self-harm, illegal) before any image is generated. Clean prompts pass through to Replicate; flagged prompts are rejected with a reason and never reach the model.
When to use it
Use it when end users can submit free-text prompts to an image generator and you need a hard guardrail before spending compute or risking unsafe output. It is the cheapest place to stop a bad request: before the model runs.
How it works
- 1A webhook receives the user's prompt, user ID, and request metadata.
- 2An OpenAI moderation classification scores the prompt against each policy category.
- 3A logic branch checks whether any category exceeds its threshold.
- 4If clean, the prompt is dispatched to Replicate to start the generation.
- 5Every verdict (allow or block) is written to Postgres with the prompt, scores, and timestamp.
- 6The webhook responds to the caller with either the prediction ID or a structured rejection.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect ReplicateImage, video, and model inference.
- 4Connect PostgresAny Postgres URL — query, write, migrate.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, 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.