Champion Job-Change Watcher — daily LinkedIn company-change detection
A champion moving to a new company is one of the highest-conversion outbound signals in B2B. They already trust your product; their new employer doesn't. This agent walks your champion + customer list daily, detects company changes from LinkedIn, and pings Slack the morning it happens.
The outcomes on their scorecard
A champion at their new company is the warmest possible cold outreach. They know you, they have influence, their new employer is a clean logo.
9am Slack ping means you hear about the move before your team logs in. The right time to reach out is the first 2–4 weeks of the new role.
20 contacts per daily run. At 400 tracked people, every contact is checked every ~3 weeks — the right cadence for catching moves without burning credits.
Writes signals to a table, posts to Slack, stops. Activation (reach-out, sequencing, account creation) is a separate motion downstream.
How the work gets done
The best outbound lead is a champion who just changed companies. They already used your product, already evangelized it, already know the rough deployment shape — and their new employer is a fresh logo where they have purchasing influence. The window to catch it is narrow: too early and they're still onboarding; too late and someone else sold the new company a competitor. This agent watches your tracked_contacts table (your hand-picked champions + customers) once a day, walks the 20 oldest-checked rows, fetches each contact's LinkedIn profile, and compares the current company to the snapshot stored in your DB. Changes get written to a `job_change_signals` table and surfaced in Slack at 9am — usually before your team is at their desks. Bounded to 20 per run so at 400 tracked contacts every person gets checked every ~3 weeks, the right cadence for catching moves without burning API spend. Detection-only by design: pair with your outbound stack for the activation half.
Daily LinkedIn company-change detection across a hand-picked list of champions + customers. Bounded batch keeps cost predictable, atomic per-row updates mean a mid-run crash never loses data. The agent does detection only — activation is a separate motion downstream.
Your new teammate
Champion Job-Change Watcher
Daily scheduled agent that walks the oldest-checked rows in tracked_contacts, fetches LinkedIn profiles, detects company changes since last check, writes signals to job_change_signals, and posts a Slack summary. Detection-only — activation is a separate downstream agent.
What it runs on
This hire is assembled from the public toolkit. Every piece below is a tool your own agents can call too.
How setup works
- 01
Claim the hire
One click. No questionnaire. The brief is already written from your business, and you can edit it before you build if you want to.
- 02
Your hire deploys itself
Agents, tools, schedules, memory, hand-off queues and the database schema are provisioned into your workspace automatically, then the first real run fires while you watch.
- 03
Hand it the keys it still needs
You land in chat with your hire and its findings. 2 setup tasks — connecting your outreach tools, picking where it reports — are done conversationally, whenever you want.
Other hires that pair well
Outbound Research Analyst
Turn the people writing about your problem on LinkedIn — and the ones quietly liking and commenting on posts about your space, including your competitors' — into a qualified outbound pipeline: scraped daily, enriched with verified email, scored against your ICP, and added to both your LinkedIn outreach (HeyReach) and cold email (Instantly) campaigns — automatically and deduped.
X (Twitter) profile qualifier and enricher
Hand any X username to this agent and get back a qualified, ICP-scored lead with a verified email and a resolved LinkedIn profile.
LinkedIn profile qualifier and enricher
Hand any LinkedIn profile URL to this agent and get back a qualified, ICP-scored lead with a verified email and a website summary attached.
Every hire is assembled from the same toolkit.
Same data sources, same database, same memory, schedules and queues. Point your own agent at the MCP endpoint and wire it your way instead.