SOCIAL MEDIA
Page on-call when negative community sentiment spikes
Sweeps recent community mentions on a schedule, measures the share that are angry or negative.
How it runs
The automated pipeline, trigger to output.
- TriggerEvery 15 minutes
- ActionSearch recent brand mentions with ExaExa
- ActionClassify each mention with OpenAIOpenAI
- LogicCompute negative share and compare to threshold
- ActionOpen PagerDuty incident on breachPagerDuty
- OutputPost sentiment summary to SlackSlack
What it does
Pulls the last hour of brand mentions across the public web and social platforms, runs each through sentiment scoring, and computes the negative share. If that share jumps past your threshold (a brewing pile-on, an outage backlash), it opens a PagerDuty incident and posts a summary to Slack so on-call sees it immediately.
When to use it
Use this as a sentiment smoke alarm. Individual angry posts are normal; a sudden cluster is a signal. This catches coordinated backlash or an incident-driven spike before it trends.
How it works
- 1A schedule fires every 15 minutes.
- 2Exa searches the public web and social mentions of your brand from the last interval.
- 3OpenAI classifies each mention as positive, neutral, or negative and tags a likely cause.
- 4A logic step computes the negative share and compares it to the threshold.
- 5If breached, PagerDuty opens an incident tagged with the dominant cause.
- 6A Slack message posts the negative rate, top quotes, and a link to the incident.
Set it up
What you configure once, before turning it on.
- 1Connect ExaNeural search across the web.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect PagerDutyIncidents, on-call, escalations.
- 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.