prospecting

---
name: prospecting
description: Use when building, qualifying, or scoring a prospect list — B2B SaaS, general B2B, local SMB, or early first-customer discovery — for ICP targeting, lead qualification, or outbound list building.
category: Marketing
version: 1.0.0
tools: []
---

# Prospecting

Build qualified, verified, scored prospect lists across four motions: B2B SaaS, general B2B, local small business, and early-stage demand-signal discovery (finding first customers from public pain signals). Turn an ICP definition into a ready-to-outreach lead sheet using the right sources, qualification signals, and compliance posture for each motion.

## Before Starting

Search the Knowledge Base for existing product-marketing context (ICP, audience, positioning) before asking questions. Only ask about what isn't already covered.

## Pick the Branch

Prospecting motions fork at intake. Pick one branch based on who is being sold to:

| Branch | Sell to | "Qualified" looks like | Primary sources |
|---|---|---|---|
| SaaS | Other SaaS / digital businesses | ICP fit + tech-stack match + growth signals (funding, hiring, product velocity) | LinkedIn, BuiltWith, Crunchbase, Apollo, Clay, Clearbit, ProductHunt |
| B2B | Non-SaaS B2B (services, manufacturers, enterprises, mid-market) | Industry + size + geo fit + buying signals (trigger events, vendor changes) | Apollo, ZoomInfo, Clay, Clearbit, LinkedIn Sales Nav, industry directories |
| Local SMB | Local small businesses (shops, gyms, restaurants, clinics, salons, services) | Active business + website status + proximity + decision-maker access | Google Maps, Yelp, local directories, Facebook, business websites |
| Demand-signal | Early-stage: first customers, design partners, beta users | A cited public source of the exact pain/demand/timing signal, not just firmographic fit | Forums, communities, reviews, GitHub issues, job posts, launch announcements |

For a hybrid motion, pick the dominant branch and borrow qualification signals from the other. For early-stage first-customer or design-partner search, default to Demand-signal — evidence over list coverage.

## Shared Framework (all branches)

Five phases apply to every engagement; tools and qualification signals change per branch, phases don't.

**Phase 1 — Define the ICP.** Gather: firmographic fit (industry, size, revenue band, geography, business model); technographic fit for SaaS (tools they already use or lack); buying signal — why now (trigger event, funding, hiring, dissatisfaction with current vendor, expansion); decision-maker profile (role, seniority, priorities); disqualifiers (what makes a prospect a clear skip). Output a one-paragraph ICP statement plus a pass/fail checklist. Don't move to discovery without it.

**Phase 2 — Build the candidate list.** Source 2–3x more candidates than the target count — qualification culls aggressively. SaaS/B2B: combine 2–3 sources for cross-verification — Apollo or ZoomInfo for firmographics, Clearbit or Clay for enrichment, LinkedIn Sales Navigator for decision-maker mapping. Local SMB: start with Google Maps for the category and area, cross-check against Yelp, the business website, social pages, and public directories. When the quality bar is high, smaller is better — 25 verified leads beats 250 mostly-junk ones.

**Phase 3 — Qualify each candidate.** Score every candidate against the ICP checklist and attach evidence (a source URL or two) for each qualification — never assert without backing. Confidence levels: **High** = confirmed by at least two independent sources or an official business page; **Medium** = one credible source plus consistent search evidence; **Low** = incomplete or ambiguous evidence, flag what remains uncertain. For B2B/SaaS email contacts, always verify deliverability before adding to the final list — don't ship leads with invalid or risky emails.

**Phase 4 — Score and prioritize.** Applies to SaaS, B2B, and Local SMB:

| Score | Definition |
|---|---|
| Hot | Strong ICP fit + clear buying signal + accessible decision-maker + verified contact |
| Warm | ICP fit + softer or older signal + verifiable contact |
| Cold | Loose ICP fit OR no clear signal OR unverified contact |
| Skip | Disqualifier hit (out of ICP, closed business, duplicate, low confidence) |

Default target ratio: ~20% Hot, ~30% Warm, rest Cold/Skip. The Demand-signal branch scores differently — 0–100 demand-fit, not Hot/Warm/Cold.

**Phase 5 — Output the lead sheet** (SaaS/B2B/Local SMB — Demand-signal ships an evidence report instead). Default to a markdown table in chat; switch to CSV when the list exceeds 25 rows or a file is requested. Always add a **Top outreach targets** section — the top 3–5 hot leads with one sentence each on why to reach out first. Every lead sheet includes: score, business/company name, contact (where applicable), why-it's-a-prospect, source(s), confidence, last-verified date.

## Compliance Guardrails — read first, every engagement

1. No bulk scraping of LinkedIn, Google Maps, paywalled sites, or rate-limited APIs. Treat the browser as an assisted research tool, not a scraper.
2. No CAPTCHA, login-wall, or bot-protection bypass. Work only with what's publicly visible.
3. Public business contact channels only — info@, hello@, contact@, and named-role emails published on the business's own site. Personal/private emails require a lawful basis (existing relationship, opt-in).
4. GDPR / CAN-SPAM / CASL aware — capture and retain the source URL and date for every contact added to a list; required for downstream outreach compliance.
5. No reselling extracted data from Google Maps, LinkedIn, or any platform whose terms prohibit it. List-building for the user's own outreach is fine; productizing the list to sell is not.
6. Rate-limit even on public sources — don't fingerprint as a bot.
7. No breached, leaked, or unprovenanced data — don't source from breached datasets, scraped-contact marketplaces, or list brokers with no source lineage. Licensed B2B data providers (Apollo, ZoomInfo, Clearbit, Clay) are fine within their ToS and with a lawful basis; the ban is on illicit/unprovenanced data, not legitimate enrichment vendors.
8. Never target or infer sensitive traits — don't qualify, segment, or personalize on health, financial hardship, political belief, sexuality, religion, or other protected attributes, even when a public post reveals them.

## Inputs to Collect

If missing, ask once, then infer reasonable defaults and continue: branch (SaaS / B2B / Local SMB / Demand-signal); ICP description; target count (default 25 for SaaS/B2B, 15 for Local SMB); geography (essential for Local SMB, useful for B2B); tools available (Apollo, Clay, ZoomInfo, Hunter, Truelist — default to free + browser); output format (chat table default, or CSV); buying-signal preference (funding rounds, hiring, recent move, etc.).

## Tool Selection Quick Picks

Apollo and ZoomInfo for B2B/SaaS firmographic and contact discovery; Clay for multi-source enrichment, waterfall lookups, and custom scoring; Clearbit for email-to-company enrichment; Hunter or Snov for email-pattern guessing; Truelist for deliverability validation before outreach; LinkedIn Sales Navigator for manual decision-maker mapping (no scraping); BuiltWith/Wappalyzer for tech-stack qualification and Crunchbase for funding signals (SaaS branch); GitHub stargazers/forks of competitor repos (dev-tool SaaS); Google Maps plus browser for Local SMB discovery.

With no enrichment tools, lean on browser-assisted research with public sources — company website, About page, LinkedIn company page, news mentions. Slower but works.

## Output Formats

Chat table, SaaS/B2B (≤25 rows): score, company, industry, size, signal, contact, email status, source, confidence.
Chat table, Local SMB (≤15 rows): score, business, category, area, website status, website/social, phone, why prospect, confidence.
CSV, above 25 rows or on request: SaaS/B2B columns add domain, country, contact_title, source_urls, verified_date, notes; Local SMB columns add distance, social_urls, source_urls, verified_date, notes.

Always include after the table: **Top outreach targets** (top 3–5 hot leads with a one-sentence rationale each), **search parameters** (branch, ICP, location/radius, target count, date generated), **open questions** (anything unverified that the user should check).

## Quality Checks Before Finalizing

Duplicates removed (by domain for SaaS/B2B, by business + address for Local SMB); every "Hot" lead has a verified contact and a source URL; no lead has a failed email-verification result (move to a separate "invalid" bucket and flag it); no "Hot" lead lacks a clear buying signal; confidence levels are honest — "High" requires two independent sources, not two of your own searches; no leads sourced from prohibited bulk scraping; source URL and date captured for every contact (GDPR/CAN-SPAM lineage); final count matches the request or the shortfall is explained by the quality bar.

## Common Mistakes

Starting discovery without an ICP (vague criteria qualify the wrong things); treating Apollo/ZoomInfo as authoritative without cross-checks (they go stale — verify before scoring "Hot"); adding contacts without email verification (bounces tank cold-email reputation fast); bulk scraping LinkedIn or Google Maps (real risk of account suspension and ToS violation); mixing branches (don't apply Local SMB website-status scoring to a B2B SaaS prospect); "Hot" labels without buying signals (ICP fit alone isn't enough — the signal makes the timing right); no source URLs (every claim should be traceable; future outreach depends on this lineage); ignoring quiet hours / time zone at outreach handoff; forgetting consent/lineage records (needed for GDPR DSARs and CAN-SPAM audits).

## Task-Specific Questions

1. Which branch — SaaS, B2B, Local SMB, or Demand-signal (early-stage, finding first customers)?
2. What's the ICP, or should context be pulled from existing product-marketing knowledge?
3. How many qualified leads are wanted?
4. What tools are available (Apollo / Clay / ZoomInfo / Hunter / Truelist / browser only)?
5. What's the triggering buying signal that matters most?
6. Geography or radius (Local SMB / B2B)?
7. Chat table or CSV?