SOCIAL MEDIA
Cross-platform negative sentiment watcher with comms escalation
Continuously samples Discord channels and X mentions, clusters emerging negative themes.
How it runs
The automated pipeline, trigger to output.
- TriggerEvery 15 minutes
- ActionPull recent Discord channel messagesDiscord
- ActionSearch X brand mentionsExa
- ActionClassify sentiment and cluster into themesOpenAI
- LogicKeep themes over negativity + volume threshold
- OutputEscalate emerging themes to comms SlackSlack
What it does
Watches your community's two loudest surfaces — Discord and X — and surfaces *emerging* negative themes before they become a fire. Instead of pinging on every angry message, it clusters complaints into themes (e.g. "billing double-charge", "app crash on launch") and only escalates a theme once it crosses a volume and negativity threshold in a short window.
When to use it
Run it when your community is large enough that no single person can read every channel, and you need comms or support leadership to hear about a brewing issue within minutes rather than the next morning.
How it works
- 1A schedule fires every 15 minutes.
- 2It pulls recent messages from the watched Discord channels and searches X for brand mentions via Exa.
- 3An LLM step classifies each item's sentiment and assigns it to a theme cluster.
- 4A logic step keeps only themes whose negative volume exceeds the threshold for the window.
- 5Qualifying themes are posted to the comms Slack channel with a one-line summary, message count, sentiment trend, and direct evidence links.
Set it up
What you configure once, before turning it on.
- 1Connect DiscordCommunity channels + voice + bots.
- 2Connect ExaNeural search across the web.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect SlackChannels, DMs, threads, mentions.
- 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
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.