B2B Prospecting System
Claude API × B2B Prospecting

Find your next client
in seconds

Claude just changed how B2B prospecting works. Most agencies blast generic emails to random lists. The ones winning in 2026 understand prospects faster.

Get the full system →
Enter your info to unlock the Claude lead enrichment workflow, prompts, MCP setup, and full framework.

Leads stored in HubSpot. No spam. Ever.

Welcome —

The Claude Prospecting System

The exact workflow, prompts, MCP setup, and enrichment framework used to find and close B2B clients using AI — in seconds, not hours.

🔍
ZoomInfo
Company & contact data
🏺
Clay
Data enrichment
🤖
Claude API
Research + generation
🟠
HubSpot
CRM + sequences
The Workflow

6 Steps From List to Closed Deal

This is the end-to-end process. Each step feeds the next. The whole thing runs in minutes once it's set up.

Step 01
Pull target companies from ZoomInfo
Filter by industry, company size, tech stack, revenue, and geography. Export companies that match your ICP criteria with decision-maker contact info.
ZoomInfo
Step 02
Enrich company data via Clay
Run each company through Clay waterfalls — scrape their website, pull LinkedIn data, check hiring signals, and stack rank by ICP fit score.
Clay
Step 03
Claude researches each URL
Connect Claude via MCP to the enriched list. Claude visits each website and analyzes their content strategy, tech stack gaps, and growth signals in real time.
Claude API
Step 04
Claude identifies specific weaknesses
For every company, Claude generates a breakdown of service gaps, competitive blind spots, and quick-win opportunities specific to your offering.
Claude API
Step 05
Generate hyper-personalized outreach
Claude writes first-touch emails, audit reports, and pitch angles using each company's real data. Every message references something specific to them.
Claude API
Step 06
Route qualified leads into HubSpot
Enriched contacts flow into HubSpot with deal stage, fit score, and Claude-generated notes pre-populated. Sequences launch automatically.
HubSpot
Prompt Engineering

The Prompts That Do The Work

These aren't generic templates. Each prompt is engineered to extract specific, actionable data from a company profile. The output is structured JSON that maps directly to HubSpot deal properties.

How to use these: Each prompt accepts variable inputs wrapped in double curly braces — filled in by Clay or your enrichment pipeline before being sent to Claude. Force JSON-only output in every system prompt to avoid inconsistent formatting at scale.
01 — Company Research & Gap Analysis Foundation Prompt

The base prompt. Send this when you have a company URL and want to identify specific weaknesses you can sell against. Works for any service-based agency. Run this first — all other prompts build on its output.

Company Research Prompt Input: URL + Industry
# System
You are a B2B growth analyst specializing in {{your_service}}.
Analyze companies and identify specific, actionable gaps.
Return structured JSON only. No preamble, no commentary.

# User
Analyze this company and return a JSON object:

Company URL: {{company_url}}
Industry: {{industry}}
Company Size: {{employee_count}}
Our Service: {{service_category}}

Return:
{
  "gap_analysis": [top 3 specific gaps related to our service],
  "growth_signals": [hiring, content velocity, ad spend indicators],
  "decision_maker_angle": [what CEO vs CMO vs VP cares about],
  "fit_score": number 1-10,
  "fit_reasoning": "one sentence",
  "urgency_signals": [evidence they need this now]
}
02 — Personalized Cold Email Generator Outreach Prompt

Takes the gap analysis output and turns it into a high-conversion first-touch email. The key is referencing something specific — not just their company name. Claude will use the actual pain point you found.

Cold Email Prompt Input: Gap Analysis JSON
# System
You write cold emails that get replies. No fluff. No generic openers.
Lead with a specific observation. Keep it under 100 words.
Never use "I hope this email finds you well."
Never mention your company in the first sentence.

Contact Name: {{first_name}}
Company: {{company_name}}
Their Biggest Gap: {{gap_analysis[0]}}
Growth Signal: {{growth_signals[0]}}
Our Offering: {{service_pitch}}

Format as JSON:
{
  "subject_line": "...",
  "email_body": "...",
  "ps_line": "optional 1-line P.S.",
  "followup_angle": "what to reference in follow-up #2"
}
03 — Mini Audit Report Generator High-Value Asset

The highest-converting outreach asset. A free 1-page audit specific to their business. Claude generates the full content automatically — you send it as a PDF or landing page. Dramatically increases reply rate vs. plain email.

Audit Report Prompt Input: Full Company Profile
# System
You are a senior consultant writing a free audit report.
Be specific, credible, and show your work. Avoid vague statements.
Every finding must include a severity level and a recommended action.

Company: {{company_name}}
URL Scraped: {{scraped_content}}
Tech Stack: {{tech_stack}}
Competitors: {{competitor_list}}
Our Service Focus: {{service_category}}

Return JSON:
{
  "executive_summary": "2-3 sentences",
  "findings": [{ issue, severity, recommendation }],
  "quick_wins": [3 things they can do this week],
  "competitive_gap": "what competitors do that they don't",
  "estimated_impact": "if they fixed the top issue, what happens"
}
04 — ICP Scoring & Prioritization Batch Prompt

Use this to rank a batch of companies so your team focuses on the highest-leverage targets first. Feed 10–50 companies at once. The output tells you exactly where to spend your time.

Batch Scoring Prompt Input: Company Array
# System
You are an ICP scoring engine. Score companies ruthlessly.
A 10 = budget, urgency, exact service match.
A 1 = wrong size, wrong industry, or no evidence of pain.
Return only the JSON array, sorted by score descending.

ICP Definition: {{icp_description}}
Our Service: {{service_description}}
Company List: {{company_array_json}}

Return:
[{
  "company": "...",
  "score": 1-10,
  "tier": "A" | "B" | "C",
  "top_reason": "why they scored high",
  "disqualifier": "biggest risk or gap"
}]
MCP Connectors

How to Connect Claude to Your Stack

MCP (Model Context Protocol) is what lets Claude natively talk to ZoomInfo, Clay, HubSpot, and your other tools without copy-pasting data between systems. Here's how each connector works in practice.

What MCP actually is: MCP gives Claude direct read/write access to external tools in real time. Instead of you exporting a CSV from ZoomInfo and pasting it into Claude, Claude pulls the data itself, analyzes it, and writes the results back to HubSpot — all in one conversation. It's the difference between a research assistant and a fully autonomous workflow.
🔍
ZoomInfo MCP
Connect via ZoomInfo's API or through Clay as a pass-through. Claude queries company and contact data directly by ICP filter — no manual exports required.
  • Query companies by SIC code, revenue, tech stack
  • Pull decision-maker contact data in real time
  • Search by intent signals (in-market buyers)
  • Export directly to enrichment pipeline
🏺
Clay MCP
Clay's API lets Claude trigger enrichment waterfalls, check column outputs, and build table rows autonomously. Best used with Claude as the AI column inside your table.
  • Trigger waterfall enrichment per row
  • Read scraped website content as input
  • Write Claude's output back to Clay columns
  • Trigger downstream actions (email, Slack)
🟠
HubSpot MCP
The HubSpot MCP lets Claude create contacts, update deal properties, write notes, enroll contacts in sequences, and read CRM context — without leaving Claude's interface.
  • Create contacts with full enrichment data
  • Write Claude's gap analysis to deal notes
  • Enroll contacts into email sequences
  • Update deal stage and fit score properties
🌐
Web Fetch MCP
Claude's built-in web fetch capability lets it visit any company URL and read page content directly. This is how Claude researches a company without you copying anything.
  • Scrape homepage, about, pricing, blog pages
  • Read job postings for growth signals
  • Analyze competitor pages for comparison
  • Pull LinkedIn company pages for signals
What a Live MCP Session Looks Like

This is a real Claude + MCP prospecting session. One prompt. Claude handles everything end to end.

Live MCP Session Example Claude Desktop / Claude.ai
User: Pull the top 20 ecommerce brands from ZoomInfo doing
$5M–$50M revenue with an Amazon presence, founded after 2018.
Score them against our ICP. Write a first-touch email for the top 5.

Claude: [calls ZoomInfo MCP → pulls 20 companies]
[calls web_fetch on each company URL]
[runs gap analysis prompt on each]
[scores and ranks all 20 by fit]
[generates 5 personalized cold emails]
[creates 5 contacts in HubSpot with notes]
[enrolls all 5 in outbound sequence]

# Total time: ~45 seconds. Previously: 4–6 hours.
Know Before You Build

Real Limitations of This System

This workflow is powerful but not magic. Here's exactly where it breaks down and how to work around each limitation before it costs you a deal.

Limitation 01
Context Window Limits
Claude can process ~200K tokens per conversation. Feed it 100 companies with full scraped content and output quality degrades toward the end.
Batch in groups of 10–15 companies max. Use Claude Haiku for initial scoring, Sonnet for writing.
Limitation 02
No Real-Time LinkedIn Data
Claude cannot directly access LinkedIn profiles or activity feeds without a third-party integration. Scraping LinkedIn at scale violates their ToS.
Use Clay's LinkedIn enrichment columns to pull data first, then pass that structured data to Claude as input.
Limitation 03
Hallucinated Company Data
If Claude can't access a URL (paywalled, JS-rendered, slow load), it may generate plausible-sounding but inaccurate company details from training data.
Require a confidence field in your JSON schema. Pre-scrape with Clay before sending to Claude.
Limitation 04
Rate Limits at Scale
At 1000+ companies you'll hit Claude API rate limits, ZoomInfo API quotas, and Clay row limits simultaneously. Parallel processing breaks if not managed.
Implement exponential backoff in your Clay → Claude webhook. Run batches during off-peak hours.
Limitation 05
Output Consistency
Claude is non-deterministic. Two runs on the same company produce different output, breaking downstream CRM automations that expect exact field names.
Use strict JSON schema validation. Force enum values for categorical fields like tier and urgency level.
Limitation 06
Stale Personalization
Claude will write confident emails referencing a "product launch" based on a blog post published 18 months ago. Prospects notice outdated references immediately.
Pass {{content_date}} to Claude and instruct it to flag anything older than 90 days.
Bottom line: This system is 10× better than manual prospecting, but it requires a human QA layer before anything reaches a real prospect. Use Claude to generate at scale, then do a 30-second spot check on your A-tier accounts before sending. The system finds the needle in the haystack — you still throw the pitch.
Enrichment Playbook

Every Type of Enrichment You Can Run

Enrichment is the intelligence layer between raw company data and actionable outreach. Here are the specific types of enrichment this system runs, what Claude does with each one, and the exact pitch angle it unlocks.

01
Tech Stack Enrichment
Source: BuiltWith via Clay · Clearbit · Manual scrape
What You Pull
E-commerce platform (Shopify, Magento, BigCommerce)
Marketing automation stack (Klaviyo, HubSpot, Mailchimp)
Advertising pixels (Meta, Google, TikTok, Amazon DSP)
Analytics tools (GA4, Heap, Amplitude)
Customer support stack (Zendesk, Gorgias, Re:amaze)
What Claude Does With It
Identifies tech debt — deprecated tools in use
Spots missing tools your service fills
Infers budget signals from premium tool usage
Detects which competitors they use vs. don't
Ranks by technology maturity level
Pitch angle: "They're running Klaviyo but have no Amazon DSP pixel — they're leaving retargeting revenue on the table. Lead with that."
02
Hiring Signal Enrichment
Source: LinkedIn Jobs API · Clay · Scraped job boards
What You Pull
Active job postings by department
Roles posted in last 30/60/90 days
Specific skill requirements in job descriptions
Headcount growth rate (year-over-year)
Recent leadership hires (VP, Director level)
What Claude Does With It
Detects growth phase (scaling vs. consolidating)
Identifies pain points hidden in job descriptions
Flags new decision-makers (new VP = new budget)
Predicts service gaps from unfilled roles
Scores urgency based on role posting velocity
Pitch angle: "They've posted 3 Amazon Ads roles in 60 days and haven't filled any — they need capability now, not in 6 months. Offer to bridge the gap."
03
Content & SEO Enrichment
Source: Ahrefs MCP · Semrush · Screaming Frog · Claude web fetch
What You Pull
Domain rating and backlink profile
Organic traffic trend (growing vs. declining)
Top performing pages and keywords
Content publishing frequency
Paid search spend estimates
What Claude Does With It
Identifies content gaps vs. top competitors
Spots declining traffic as urgent pain signal
Finds keyword opportunities being missed
Assesses content quality and consistency
Benchmarks against industry averages
Pitch angle: "Their organic traffic dropped 34% in 6 months but ad spend is unchanged — they're burning budget trying to compensate. That's your opening."
04
Social Presence Enrichment
Source: Clay Social · Scraped profiles · Engagement APIs
What You Pull
Follower counts across all platforms
Posting frequency by channel
Engagement rate benchmarks
Last post date and activity signals
Ad library presence (are they running paid?)
What Claude Does With It
Identifies dormant channels as opportunity
Benchmarks engagement vs. competitors
Detects content strategy gaps
Flags accounts not running paid ads
Identifies brands losing social share of voice
Pitch angle: "They have 80K Instagram followers but haven't posted in 47 days and run zero paid ads. Their social funnel is completely dead."
05
Revenue & Funding Enrichment
Source: Crunchbase · PitchBook · ZoomInfo Financials · Clay
What You Pull
Estimated ARR or revenue range
Funding rounds and total raised
Last funding date and lead investors
Revenue growth trajectory
Burn rate and runway estimates
What Claude Does With It
Infers budget availability for services
Identifies post-funding growth pressure
Flags Series A/B companies in growth mode
Disqualifies companies at high churn risk
Estimates deal size range for your proposal
Pitch angle: "They raised a $12M Series A 8 months ago and haven't grown their marketing team. That funding is sitting there. They're under pressure to deploy it."
06
Amazon Marketplace Enrichment
Source: Jungle Scout · Helium 10 · Amazon scrape · Seller Central public data
What You Pull
Amazon seller status (1P, 3P, or absent)
Estimated Amazon revenue
BSR and category ranking
Listing quality score (A+, images, copy)
Sponsored ad presence and share of voice
What Claude Does With It
Scores Amazon listing optimization gaps
Identifies missing A+ content or brand store
Compares ad coverage vs. category leaders
Flags brands with zero Amazon presence
Estimates revenue lift potential
Pitch angle: "Their #1 competitor has A+ content, Brand Store, and 300+ sponsored placements. This brand has none of it and is competing on the same keywords."
System Output

What This System Produces Per Company

Every company that moves through the pipeline gets a complete intelligence package — not just a name and email, but a full brief your reps can act on immediately.

🔎 Research Layer
Full tech stack analysis
Social presence scorecard
Hiring pattern signals
Revenue estimate + source
Decision-maker map
Competitor comparison
📝 Outreach Assets
Personalized cold email
Custom mini audit report
Pitch angle by growth stage
3-step follow-up sequence
Proposal outline
LinkedIn connection message
📊 Scoring Data
ICP fit score (1–10)
Budget likelihood rating
Buying intent signals
Urgency tier (A / B / C)
Recommended next action
HubSpot deal properties

The advantage isn't
who prospects more

"In 2026 the advantage will not go to the sellers that prospect more. It will go to the one that understands prospects faster."
— Noah Wickham, MAGAI

This system processes entire markets in seconds. Claude identifies their biggest gaps, then helps you build the perfect solution. Automatically.

Follow Noah on LinkedIn →