SOCIAL MEDIA
Agent-led cross-platform authenticity investigation with a takedown dossier
An autonomous agent investigates a suspicious handle across multiple platforms and the open web, correlates linked accounts and reused assets.
How it runs
The automated pipeline, trigger to output.
- TriggerInvestigator submits seed handle
- ActionSearch web for reused avatar, bio, and linksExa
- ActionCross-check additional sourcesBrave Search
- ActionInspect candidate profiles to confirm linkageBrowserbase
- LogicClassify lone copycat vs. coordinated network
- ActionCompile cross-platform dossierNotion
- OutputOpen Linear takedown task linking the dossierLinear
What it does
Given one suspicious handle, an agent expands the investigation: it searches for the same avatar, bio text, and links across other platforms, maps the cluster of connected fake accounts, and reasons about whether this is a lone copycat or a coordinated network. It outputs a structured dossier and opens tracked work to act on it.
When to use it
Use this when a single fake account is likely the tip of a larger impersonation ring and a flat scraper-and-score pipeline misses the connections. It suits investigators who need judgment and pivoting, not just a checklist.
How it works
- 1A staff member triggers the investigation with a seed handle.
- 2The agent uses Exa and Brave Search to find reuse of the avatar, bio, and linked URLs across the web.
- 3The agent drives Browserbase to inspect candidate profiles and confirm linkage.
- 4It reasons over the cluster to classify lone copycat vs. coordinated network with supporting evidence.
- 5It compiles a Notion dossier of all linked accounts, assets, and findings.
- 6It opens a Linear takedown task linking the dossier and assigning the right owner.
Set it up
What you configure once, before turning it on.
- 1Connect ExaNeural search across the web.
- 2Connect Brave SearchWeb, news, image, video search.
- 3Connect BrowserbaseHeadless browsers, sessions, replays.
- 4Connect NotionPages, databases, comments.
- 5Connect LinearIssues, projects, cycles, triage.
- 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.