SOCIAL MEDIA
DM auto-responder with toxicity escalation to support
Inbound social DMs are toxicity-scored on arrival; hostile messages skip the bot and open a Zendesk ticket, while normal DMs get a screened AI reply auto-sent.
How it runs
The automated pipeline, trigger to output.
- TriggerInbound DM receivedHTTP webhook
- ActionScore incoming DM toxicity (HuggingFace)Hugging Face
- LogicIs the message hostile?
- ActionOpen Zendesk ticket for human handlingZendesk
- ActionDraft reply for non-hostile DM (OpenAI)OpenAI
- ActionRe-screen draft reply (HuggingFace)Hugging Face
- OutputSend screened reply to userSocial publishing
What it does
This workflow triages inbound direct messages before the bot ever answers. Each incoming DM is scored for toxicity. Hostile or abusive messages are pulled out of the automation entirely and handed to a human as a Zendesk ticket so a person handles the conflict. Everything else gets an AI-drafted reply that is itself screened before it is sent back to the user.
When to use it
Use it when you automate DM responses but want abusive or volatile conversations to land with a trained support agent instead of a bot, and you never want the bot's own reply to escalate a tense thread.
How it works
- 1A new inbound DM arrives via webhook.
- 2HuggingFace scores the incoming message for toxicity.
- 3A logic step checks whether the message is hostile.
- 4If hostile, a Zendesk ticket is opened with the message and the bot stays silent.
- 5If not, OpenAI drafts a reply.
- 6HuggingFace re-screens the draft so the bot's response stays clean.
- 7The screened reply is sent back to the user on the platform.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 3Connect ZendeskTickets, queues, knowledge base.
- 4Connect OpenAIModels, embeddings, files.
- 5Connect Social publishingCross-post to X, LinkedIn, Instagram, TikTok, and 4 more in one call.
- 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 Social Media workflows
A/B carousel cover variants from one brief
Takes a single approved brief and uses an LLM to write three distinct cover-slide headlines, renders a carousel cover for each, and logs the variants to Airtable for an A/B test.
Localized carousel variants per target market
From one approved master brief, translates the copy into each target locale, renders a localized carousel per market, and publishes each to its region's platform account.
Multi-Platform Comment Escalation Router
Ingests inbound comments and replies from your connected social platforms, classifies each for legal or PR risk.
Post-event Discord attendance recap and host digest
After a synced calendar event ends, reconciles who RSVP'd against who actually showed, posts a thank-you recap in Discord, and emails the host a digest of attendance and no-shows.
Agent-Driven Comment Policy Review Queue
An agent reviews ambiguous comments against your brand's response policy, decides whether to auto-clear, draft a reply for approval, or escalate, and routes its decision…
Carousel render with brand-safety pre-check
Before rendering, an LLM checks the brief copy against brand and policy rules; clean briefs render and archive to S3, flagged briefs route to a review queue instead.
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.