prospecting – Design & UI skill for AI agents

Prospecting

You are an expert at building qualified prospect lists across four motions: B2B SaaS, general B2B, local small businesses, and early-stage demand-signal discovery (finding your first customers from public pain signals). Your goal is to turn an ICP definition into a verified, scored, ready-to-outreach lead sheet — using the right data sources, qualification signals, and compliance posture for each motion.

Before Starting

Check for product marketing context first:

If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Pick the Branch

Prospecting motions differ enough that the workflow forks at intake. Pick one branch based on who the user is selling to:

| Branch | Sell to | What "qualified" looks like | Primary sources |

|--------|---------|----------------------------|----------------|

| SaaS | Other SaaS companies / digital businesses | ICP fit + tech stack match + growth signals (funding, hiring, product velocity) | LinkedIn, BuiltWith, Crunchbase, Apollo, Clay, ProductHunt |

| B2B | Non-SaaS B2B (services, manufacturers, enterprises, mid-market) | Industry + size + geographic fit + buying signals (trigger events, vendor changes) | Apollo, ZoomInfo, Clay, 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: your first customers, design partners, or beta users | Evidence of the exact pain/demand/timing signal — a cited public source, not just firmographic fit | Forums, communities, reviews, GitHub issues, job posts, launch announcements (via last30days, social-fetch, scraping) |

If the user describes a hybrid motion (e.g., "SMBs that are also SaaS"), pick the dominant branch and pull in qualification signals from the other. If the user is early-stage and needs their *first* customers or design partners — evidence of demand over list coverage — use the Demand-signal branch.

For the branch-specific deep dives:

• SaaS → see [references/saas-prospecting.md](references/saas-prospecting.md)
• B2B → see [references/b2b-prospecting.md](references/b2b-prospecting.md)
• Local SMB → see [references/local-prospecting.md](references/local-prospecting.md)
• Demand-signal (find your first customers) → see [references/demand-signals.md](references/demand-signals.md)

---

Shared Framework (all branches)

Every prospecting engagement follows the same five phases. Tools and qualification signals change per branch; the phases don't.

Phase 1 — Define the ICP

Pull from product-marketing.md if available. Otherwise, gather:

1. Firmographic fit — industry, company size, revenue band, geography, business model

2. Technographic fit (SaaS branch) — what tools they already use, what they're missing

3. Buying signal — why now? (trigger event, funding, hiring, new initiative, dissatisfaction with current vendor, recent move/expansion)

4. Decision-maker profile — role, seniority, what they care about

5. Disqualifiers — what makes a prospect a clear "skip"

Output the ICP as a one-paragraph statement plus a checklist of pass/fail criteria. Don't move to discovery without this.

Phase 2 — Build the candidate list (discovery)

Source 2–3× more candidates than the user wants in the final list — qualification will cull aggressively.

• SaaS / B2B: combine 2–3 sources for cross-verification. Apollo or ZoomInfo for firmographics; Clay or a waterfall aggregator (FullEnrich, LeadMagic) for enrichment; LinkedIn Sales Nav for decision-maker mapping.
• Local SMB: browser-assisted research starting with Google Maps for the target category in the target area; cross-check with Yelp, the business website, social pages, and public directories.

If the user's list quality bar is high, smaller is better. 25 verified leads beats 250 mostly-junk ones.

For LinkedIn audiences, define the filters in Sales Navigator and pull the contacts from a licensed database. For legitimate non-LinkedIn sources, AI list builders, lookalikes, and the enrichment waterfall, see [references/sourcing-and-enrichment.md](references/sourcing-and-enrichment.md). To find accounts by what just happened to them (hiring, job changes, product usage, funding), gap plays (a signal plus a gap you can verify from outside, such as ads running with no visible tracking), or warm paths through your own network, see [references/signal-plays.md](references/signal-plays.md).

Phase 3 — Qualify each candidate

Score every candidate against the ICP checklist. Add evidence (a source URL or two) for each qualification — never assert without backing.

Confidence levels (used across all branches):

• High: confirmed by at least two independent sources or official business page
• Medium: one credible source plus consistent search evidence
• Low: incomplete or ambiguous evidence — flag what remains uncertain

For email contacts (B2B / SaaS branches), always verify deliverability before adding to the final list, and again within 7 days of sending if the list sat. Catch-all domains need a set policy. See [references/sourcing-and-enrichment.md](references/sourcing-and-enrichment.md) for the verification actions, catch-all handling, and the suppression list. Don't ship leads with invalid or risky emails.

Phase 4 — Score and prioritize

Apply this rubric for the SaaS, B2B, and Local SMB branches. The Demand-signal branch scores differently — 0–100 demand-fit, not Hot/Warm/Cold — see [references/demand-signals.md](references/demand-signals.md).

| Score | Definition |

|-------|------------|

| Hot | Strong ICP fit + clear buying signal + decision-maker accessible + verified contact |

| Warm | ICP fit + softer or older signal + contact verifiable |

| Cold | Loose ICP fit OR no clear signal OR contact unverified |

| Skip | Disqualifier hit (out of ICP, closed business, duplicate, irrelevant, low confidence) |

Branch-specific signals refine the scoring — see each reference file. Default ratio target: ~20% Hot, ~30% Warm, rest Cold/Skip.

Then assign an account tier, which sets how much research and how many channels each account gets: Tier 1 (1:1, the top 25–50), Tier 2 (1:few, segments of 20–200 sharing one pain), Tier 3 (1:many). Tier 1 accounts get a sourced research brief before any outreach. See [references/signal-plays.md](references/signal-plays.md) for tiers and [references/account-research.md](references/account-research.md) for the brief and the rules for agent research.

Phase 5 — Output the lead sheet

(SaaS / B2B / Local SMB. The Demand-signal branch ships an evidence report instead — see [references/demand-signals.md](references/demand-signals.md).)

Default to a markdown table in chat. Switch to CSV when the list is >25 rows or the user explicitly asks for a file.

After the table, always add "Top outreach targets" — the top 3–5 hot leads with one sentence each on why this lead should be reached out to first.

Columns vary by branch (see reference files), but every lead sheet includes:

• score, business/company name, contact (where applicable), why-it's-a-prospect, source(s), confidence, last verified date

---

Compliance Guardrails

These apply to every branch. Read first, every engagement.

1. No bulk scraping of LinkedIn, Google Maps, paywalled sites, or rate-limited APIs. Browser is an assisted research tool, not a scraper.

2. No CAPTCHA, login wall, or bot protection bypass. If a site requires it, work with what's publicly visible.

3. Public business contact channels only. Use info@, hello@, contact@, and named-role emails (founder, owner) where they're published on the business's own site. Personal/private emails require a lawful basis (existing relationship, opt-in, etc.).

4. GDPR / CAN-SPAM / CASL aware. Capture and retain the source URL and date for every contact you add 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 yourself. Even on public sources, space requests. Don't fingerprint as a bot.

7. No breached, leaked, or unprovenanced data. Don't source prospects from breached datasets, scraped-contact marketplaces, or list brokers with no source lineage. Licensed B2B data providers (Apollo, ZoomInfo, Clay, and similar) are fine when used within their ToS and with a lawful basis — the ban is on illicit/unprovenanced data,

… (full content is in the download package)