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

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.

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

The outcomes on their scorecard

One pipeline, two outbound channels

Every qualified lead lands in HeyReach (LinkedIn DM) AND Instantly (cold email). Default: one campaign per channel. Per-persona campaign routing is an opt-in for teams that already split their outbound by persona.

Verified emails or nothing

Email finder + verifier waterfall runs only on qualified leads. Cold email only fires when the address is deliverable; LinkedIn DM picks up the leads where the email lookup came back risky / unknown.

Three ponds, not one

Topic keywords surface the people talking about your space — which includes everyone who sells into it. So the scout also fishes where buyers give themselves away: the posts they write when they are hiring for the function, scaling the team, or describing the pain (there, the author is the lead), and the posts your named competitors publish, where everyone reacting is already shopping.

Scoring you can actually audit

A cheap profile-only gate rejects only what is provably out of region or an empty profile — no title blacklist, no vendor gate — and then the qualification skill scores the lead against your ICP description and writes the score and its rationale onto every row. A competitor is not a special case: it scores low because it would never buy, and the rationale says so.

Search terms that learn

Every run starts by asking which past terms actually produced qualified and sequenced leads, then writes fresh ones in the register that worked and drops the phrasing that pulled in commentary instead of buyers. Nothing is reused inside 14 days, so the program cannot quietly collapse onto five phrases.

A full board on day one

The first run sweeps wider on purpose: up to five searches across all three ponds, 10-12 posts, and up to 30 leads scored in one cycle, so you open the dashboard to a real pipeline instead of an empty table. And if a first run against a new ICP qualifies nobody, it still shows its work — the report lists the five closest calls with their scores, and the board has a panel for them.

02// the motion

How the work gets done

One agent owns the entire flow from "LinkedIn signal" to "in your active campaigns." Every run it fishes three ponds — the posts your buyers write when they have the problem, where the author IS the lead; the recent posts of the competitors they also evaluate, whose engagers are in-market by definition; and the topic keywords of your space — then, in the same run, enriches each new lead with LinkedIn + web research + verified email, scores it against your ICP description, and adds the qualified ones to your HeyReach LinkedIn campaign and Instantly cold-email campaign. Seven runs a weekday, deduped across both of LinkedIn's spellings of a person. The mechanical layers reject only what is provably un-contactable or provably out of region; every judgment call is the scorer's, written onto the row with its reason. Single-campaign routing by default; per-persona campaign routing is an advanced pattern the meta-agent suggests when it fits your motion.

Outbound teams already know LinkedIn is the best free intent signal — they just never act on it, because finding the posts that matter, pulling the people around them, looking up emails, checking geo + ICP fit, and pushing into the right sequencer takes a human all day. This blueprint hands that whole day to one agent, so every weekday the highest-intent profiles in your space — the people describing your problem out loud, the people engaging with your competitors, and the people engaging with the topic — land in both your LinkedIn outreach campaign and your cold-email campaign, scored and deduped, without anyone scrolling LinkedIn.

click a node to inspect
Click any node to inspect its role.
03// the roster

Your new teammate

01agent

LinkedIn Outbound Scout

Writes fresh LinkedIn search terms each run against what has actually converted, across three ponds — buyer-behavior posts where the author is the lead, competitor posts whose engagers are already in-market, and the topic space. It scrapes the people around the posts it picks, then enriches, qualifies and sequences every new lead in the same run — profile, company and web research, an ICP score with its rationale, a verified email, and the hand-off to HeyReach and Instantly. The agent chooses and reports; its skills do the per-lead fetching and writing, so a 30-lead run costs the same context as a 5-lead one.

7 schedules
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. 3 setup tasks — connecting your outreach tools, picking where it reports — are done 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