AI AGENTS
Escalate blocked image prompts to Slack for human review
When a submitted image prompt is flagged by the moderation classifier, this workflow holds the request, logs it, and posts the offending prompt to a Slack review channel…
How it runs
The automated pipeline, trigger to output.
- TriggerPrompt submitted via webhookHTTP webhook
- ActionClassify prompt for policy categoriesOpenAI
- LogicSort into clean, blocked, or borderline
- ActionDispatch clean prompts to ReplicateReplicate
- ActionRecord borderline prompt as pending in PostgresPostgres
- OutputPost borderline prompt to Slack review channelSlack
What it does
Instead of silently rejecting borderline prompts, this gate routes flagged requests to a human. Clean prompts go straight to Replicate. Anything the classifier marks as borderline is parked, logged, and surfaced in a Slack channel where a moderator can approve or deny it, keeping a human in the loop for ambiguous cases.
When to use it
Use it when false positives are costly to your users and you would rather have a moderator adjudicate gray-area prompts than auto-block them. Good for creative tools where over-blocking frustrates legitimate use.
How it works
- 1A webhook receives the prompt and user context.
- 2An OpenAI classification returns a category verdict and confidence.
- 3A logic branch sorts the prompt into clean, blocked, or borderline.
- 4Clean prompts dispatch to Replicate immediately; hard violations are denied.
- 5Borderline prompts are written to Postgres as pending.
- 6A Slack message posts the prompt and scores to the review channel with approve/reject buttons for a moderator.
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.
- 5Connect SlackChannels, DMs, threads, mentions.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI Agents workflows
Observability Cost Allocation Report
Monthly, an agent pulls Datadog and Honeycomb usage, allocates spend to teams and services by tags, writes the breakdown to Snowflake, and posts a chargeback summary to Slack.
Vendor Shortlist Matrix from a Buying Brief
An agent reads a buying brief, researches candidate vendors across the live web, and builds a scored comparison matrix in Coda ranking each vendor against your stated criteria.
Split oversized Linear epics into estimated child issues
An agent scans newly created Linear epics, breaks each one above a size threshold into discrete child issues with point estimates and acceptance criteria.
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.
Buying Brief Email to Shortlist Doc in Drive
When a buying brief arrives by email, an agent researches the market and produces a polished narrative shortlist document in Google Drive, then replies to the sender with the link.
Zoom Demo Low-Score Objection Escalation to Manager
Scores how well a rep handled objections in each Zoom demo, and only when the handling score falls below a threshold does it create a coaching task in ClickUp and alert the rep's…
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.