SOCIAL MEDIA
Sentiment-routed comment responder with toxicity safety net
Scheduled scan of new post comments classifies each by sentiment, drafts a matching reply, blocks any toxic draft, and auto-publishes the rest while logging everything to Notion.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled comment scan
- ActionClassify comment sentiment (HuggingFace)Hugging Face
- LogicBranch reply style by sentiment
- ActionDraft tone-matched reply (OpenAI)OpenAI
- ActionToxicity-screen the draft reply (HuggingFace)Hugging Face
- ActionPublish clean repliesSocial publishing
- OutputLog comment + sentiment + action to NotionNotion
What it does
This workflow reads new comments on your recent posts on a schedule, classifies each comment's sentiment with HuggingFace, and routes it: angry or negative comments get an empathetic de-escalation reply, neutral and positive ones get a lighter acknowledgment. Before anything publishes, the generated reply itself is toxicity-screened so your own response can never go out hot.
When to use it
Use it for steady community management where reply tone should match the commenter's mood, and you want a guarantee that the de-escalation replies you send to upset users are never accidentally inflammatory.
How it works
- 1A schedule trigger fires on your chosen cadence and pulls new comments.
- 2HuggingFace classifies each comment's sentiment.
- 3A logic step branches the reply style on sentiment label.
- 4OpenAI drafts the tone-matched reply.
- 5HuggingFace re-scores the draft reply for toxicity; anything over the line is dropped from the publish batch.
- 6Clean replies publish back to the platform.
- 7Every comment, sentiment label, and action is appended to a Notion log.
Set it up
What you configure once, before turning it on.
- 1Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect Social publishingCross-post to X, LinkedIn, Instagram, TikTok, and 4 more in one call.
- 4Connect NotionPages, databases, comments.
- 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 Social Media workflows
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.
Carousel render and auto-publish on Slack approval
Renders carousel variants from a brief, posts a preview to Slack for a one-click approve, and on approval publishes the chosen variant to the connected social platforms.
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.
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…
Tiered Discord event reminder fan-out (24h / 1h / live)
On a schedule, scans upcoming Discord-tracked events and DMs each confirmed attendee staged reminders at 24 hours, 1 hour, and event start.
Discord event capacity gate with automatic waitlist promotion
Enforces a seat cap on RSVPs: once an event is full, new sign-ups join a waitlist, and when someone drops out the next person is promoted, notified in Discord.
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.