LeadHaste
AdvancedNo variables to fill — paste & go

Build a Sales Navigator search strategy for your ICP

Designs a layered Sales Navigator system instead of a one-off search: account filters with the miscategorization traps flagged, persona searches with paste-ready boolean strings, a signal layer that surfaces who to message this month, saved-search alerts, and a QA protocol. Built from your real customers, not an aspirational ICP doc.

The prompt
You are a Sales Navigator power user who has built prospecting engines for dozens of B2B teams. You know most sellers use Navigator like a phone book — title plus geography, export, spray — and wonder why their lists are 40% bad fits. Real Navigator strategy is layered: firmographic filters define the universe, persona filters find the people, and signal filters (posted recently, changed jobs, company headcount growth) find the ones worth messaging THIS month. You also know the filters lie a little: titles are self-reported, industries are miscategorized, and every search needs a manual spot-check before it becomes a list.

Build my search strategy:

1. THE ACCOUNT SEARCH — the company-level filter stack for my ICP: industry (with the miscategorization traps to watch for in my space), headcount range, growth signals, geography, and any technology or funding filters that apply. Explain each choice in one line.
2. THE LEAD SEARCHES — 2–3 persona searches to run inside those accounts: title keywords with the OR-variants sellers forget (Head of / Director / VP / Lead), seniority filters, and the boolean strings to paste directly into the keyword field.
3. THE SIGNAL LAYER — which Navigator signals to stack for a 'message this month' view: posted on LinkedIn in 30 days, changed jobs in 90, company in a growth or funding moment. Rank them for my situation.
4. SAVED SEARCHES AND ALERTS — which searches to save so Navigator feeds me new matches weekly, and what a 15-minute weekly review of those alerts looks like.
5. THE SPOT-CHECK — a 10-profile manual QA protocol before any search becomes an outreach list, and the false-positive patterns my specific filters will produce.

Before you write anything, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time:
1. Describe your best 3–5 current customers — industry, size, and who championed the deal?
2. Who is the buyer persona — titles, seniority, department — and who else influences the deal?
3. What signals make a prospect hot for you — hiring, funding, tech change, leadership change?
4. Roughly how many net-new prospects per month does your outreach motion need?
5. Do you push lists into Clay, Apollo, or a sequencer, or work inside Navigator manually?

Once you have my answers, deliver all five layers with exact filter values and boolean strings I can paste today. Where my ICP answers are fuzzy, build the search around my actual customers from question 1 — lookalikes of revenue beat aspirational personas every time.

How to use it

  1. 1

    Copy the prompt into Claude, ChatGPT, or any LLM.

  2. 2

    Answer the interview — question 1 matters most; the model anchors the searches on customers who actually paid you.

  3. 3

    Build the searches in Navigator exactly as specified, run the 10-profile spot-check, and adjust the filters the QA flags.

  4. 4

    Save the searches, set the weekly alert review, and pipe qualified matches into Clay or your sequencer as the model laid out.

Best practices

  • Boolean the title keyword field generously — the person running RevOps might be titled Head of Revenue Operations, Sales Ops Manager, or GTM Systems Lead, and each miss is invisible.

  • 'Posted on LinkedIn in past 30 days' is the most under-used filter in Navigator — active posters see, and answer, their DMs.

  • Rebuild the spot-check monthly; Navigator data drifts as companies grow and people move, and a saved search silently degrades.

  • Saved-search alerts are the real engine: new matches are new-to-role or new-to-criteria, which usually means new-to-buying-mode.

Example: what this looks like in practice

A two-person SDR team at a construction-tech startup answers the interview: best customers are 100–500 person specialty contractors, champions are operations VPs, hot signal is hiring project managers. The model builds the account search (flagging that many contractors self-categorize under generic 'Construction' and some under 'Facilities'), three persona searches with boolean strings like ('VP Operations' OR 'Director of Operations' OR 'Head of Field Operations'), and a signal stack led by job-posting growth. The spot-check catches that one filter pulled residential builders — a bad fit — and after tightening, their connect-to-meeting rate improves 60% on the new lists.

Best fit

Roles
SDR / BDRRevOpsSales LeaderFounder / CEO
Company size
Startup (1–10)SMB (11–50)Mid-market (51–500)Enterprise (500+)
Audience
B2B
Industries
Any industry
Works with
Any LLM
Difficulty
Advanced

This prompt is one gear in a bigger machine. We orchestrate 20+ tools into outbound systems our clients own — and guarantee the results.

Apply for a Pilot Spot →
Prompt FAQ

Frequently asked questions

Layer it: account filters first (industry, headcount, growth) to define the universe, then persona searches inside it with boolean title variants, then signal filters — posted recently, changed jobs, company hiring — to find who's worth messaging now. Anchor every filter choice on your actual best customers rather than an aspirational ICP, and spot-check ten profiles manually before any search becomes a list.