superagnt_
// offer letter // teammate
ready to start immediately

LinkedIn Hiring-Signal Scraper — companies investing in your buyer’s role

Hiring for a role is the loudest buying signal LinkedIn gives away for free. This agent watches it daily — captures every company posting jobs in your buyer's role family, plus the hiring team behind each post — and writes them to a deduped pipeline of accounts + decision-makers ready for outreach.

LinkedIn
Claim this hireno questions · deploys on claim
01// what they own

The outcomes on their scorecard

Companies with budget allocated, right now

A job posting is proof of allocated budget for the function. Every row in `job_posts` is an account that just signed off on spending money on the role you sell into.

The decision-maker comes with the signal

Get_Hiring_Team returns the people attached to each posting — usually the hiring manager + 1–2 collaborators. Those are the buyers, not a list of every random employee at the company.

Coverage rotation, no double-scraping

Keyword × geo batches rotate across runs, so the agent never hits the same posts twice. Indices are persisted in `agent_config` BEFORE searches run — crash-safe.

Hands-off pipeline feeder

Writes to DB only. Pair with a downstream enricher and sequencer for the full motion; the scraper is the data layer that feeds the rest.

02// the motion

How the work gets done

When a company posts a job for the role you sell into, three things become true at once: they have budget allocated to that function, they have an active need that role is meant to solve, and the hiring manager is the person who decides what tools that role uses. This agent harvests that signal at scale. It rotates through keyword × geo batches several times a day, captures every new job post in your target role family, deduplicates against what's already been scraped, and — for each new post — pulls the hiring team. The output is two tables: companies that just started investing, and the names of the decision-makers on each. Pair with the `linkedin-hiring-lead-enricher` blueprint to verify emails and score by ICP fit, and `gtm-email-sequencer` to push the top band into Instantly. Works for any vendor selling to a specific role — GTM Engineers, Data Engineers, CS Managers, Founding AEs, anyone with a hiring footprint on LinkedIn.

Hiring for a role is the loudest free buying signal LinkedIn gives you — budget is allocated, the function matters, and the hiring manager is the buyer. Most teams ignore this signal because checking LinkedIn jobs daily across 4 metros and 3 keyword variants is brutal manual work. This agent automates it: rotation-batch search, dedupe, title-filter, hiring-team pull. Two tables on a daily cron.

click a node to inspect
Hiring signals harvested 2–4x daily across rotating keyword × geo batches.
03// the roster

Your new teammate

01agent

LinkedIn Hiring-Signal Scraper

Scheduled agent that searches LinkedIn 2–4x daily for job postings in a specific role family — the role family whose hiring signals my buyer is investing. Rotates through keyword × geo batches, dedupes against existing rows, captures job details + hiring team per post, and writes to `job_posts` + `hiring_leads`. Pairs with a downstream enricher and sequencer.

1 schedule
04// built on

What it runs on

This hire is assembled from the public toolkit. Every piece below is a tool your own agents can call too.

05// onboarding

How setup works

  1. 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.

  2. 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.

  3. 03

    Hand it the keys it still needs

    You land in chat with your hire and its findings. Anything it still needs is asked for conversationally, whenever you want.

06// related

Other hires that pair well

» build it yourself

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.

Wire your own agent