What it does
LinkedIn Recruiter Pipeline Tracker eliminates the manual burden of copying LinkedIn Recruiter activity into your ATS. It fetches InMail messages and response statuses from LinkedIn Recruiter, matches candidates to existing Greenhouse records by profile URL, logs activity notes for matched candidates, and creates new Greenhouse records for unmatched ones. Opted-out candidates are excluded from all processing as a GDPR guardrail. A weekly pipeline summary is published to Notion and posted to a Slack #recruiting channel, surfacing response rate, opt-out rate and Greenhouse match rate as scored findings with an LLM-generated narrative (or deterministic template fallback with no LLM configured). Built for recruiters and RevOps-style recruiting operations teams who want their LinkedIn and ATS data reconciled automatically instead of copy-pasted by hand.
Example prompts
- Run the full recruiting pipeline sync and post this week's report
- What's our InMail response rate and opt-out rate this month?
- Sync these LinkedIn candidates to Greenhouse
- Check which of these LinkedIn profiles have opted out of recruiting contact
Tools (8)
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Run the full LinkedIn Recruiter pipeline: collect InMail data + Greenhouse candidates, analyze metrics, synthesize narrative, return the full AgentResult with pipeline_report.
- get_inmail_stats — Collect InMail messages and return pipeline statistics: response rate, opt-out rate, stage breakdown. No Greenhouse sync.
- sync_candidates_to_greenhouse — Match LinkedIn InMail candidates against Greenhouse records by profile URL, log activities, create new records for unmatched. Excludes opted-out candidates (GDPR).
- generate_pipeline_report — Generate a weekly recruiting pipeline Notion report and optionally post a summary to Slack #recruiting.
- check_opt_outs — Given a list of LinkedIn profile URLs, return which ones have opted out of recruiting contact (GDPR compliance check).
- list_capabilities — List the agent's tools and capabilities.
- plan_inputs — Plan/brainstorm the inputs for a tool: returns questions, schema and a ready-to-edit example.
- discover_intent — State a freeform recruiting goal and get clarifying questions plus a concrete proposed tool input.
What you'll need to connect
This agent will ask you for the following. You enter them when you connect — they're encrypted and never shared with the creator.
- LinkedIn Recruiter Access Token · optionalLinkedIn Recruiter API access token with recruiter:read and messages:read scopes. Required for live InMail data; mock data used without it.Get this from linkedin.com's account or API settings.Paste the value as a single line.Only sent to: api.linkedin.com
- Greenhouse API Key · optionalGreenhouse Harvest API key with candidates:write, jobs:read and activities:write permissions. Required for live Greenhouse sync; mock data used without it.Get this from harvest.greenhouse.io's account or API settings.Paste the value as a single line.Only sent to: harvest.greenhouse.io
- Notion API Key · optionalNotion integration token with pages:write scope, required for publishing the weekly pipeline report to Notion.Create an internal integration in Notion (notion.so/my-integrations) and copy its secret, then share the relevant pages with that integration.Paste the value as a single line.Only sent to: api.notion.com
- Slack Bot Token · optionalSlack bot token (xoxb-...) with chat:write scope for the #recruiting channel.Create a Slack app (api.slack.com/apps), add the scopes the agent needs, install it to your workspace, and copy the bot/user token.Paste the value as a single line.Only sent to: slack.com
- Anthropic API Key · optionalOptional. Leave blank on a sampling-capable client to use the host model with no key.Create a key on the Anthropic Console API keys page (console.anthropic.com → API keys).Paste the value as a single line.Only sent to: api.anthropic.com
How you're protected
FindAgent runs these safety checks on every agent automatically. They're always on and can't be turned off.
- Prompt-injection scanning
Every request is checked for known prompt-injection and jailbreak attempts before the agent runs. This is always on.
- Secret-leak scanning
Every response is scanned for leaked API keys, tokens, and other secrets before it reaches you. This is always on.