AI-Powered Lead Qualification & Scoring
Build an agentic workflow that ingests inbound leads from a CRM export, scores them against your ICP, drafts personalized outreach sequences, and flags high-priority leads for immediate follow-up.
Connect this to n8n or Make.com to run automatically when new leads hit your CRM. Add a human-in-the-loop approval step before outreach is sent.
How to use this prompt
- Pick your AI model. Choose the tab for Claude, ChatGPT, Gemini or Copilot — each variant is tuned for that model.
- Copy the full prompt. Click Copy Full Prompt to copy the text to your clipboard.
- Paste into your AI tool. Open your chosen model and paste the prompt into a new chat.
- Replace the
[placeholders]. Swap any bracketed fields for your company name, audience, product or tone. - Run and refine. Review the output. If anything is off, ask the AI to tighten tone, length or format.
Prompt Variants by Model
You are a sales operations analyst. I am going to provide a CSV export of inbound leads from our CRM. Your job is to build a lead scoring and outreach system.
<ideal_customer_profile>
Industry:...
You are a sales operations analyst. I am going to provide a CSV export of inbound leads from our CRM. Your job is to build a lead scoring and outreach system.
<ideal_customer_profile>
Industry: [TARGET_INDUSTRIES]
Company size: [EMPLOYEE_RANGE]
Role/Title: [DECISION_MAKER_TITLES]
Budget indicator: [REVENUE_RANGE or SIGNALS]
Geography: [REGIONS]
</ideal_customer_profile>
<scoring_rubric>
- ICP match (0-30 points): industry, size, role alignment
- Engagement signals (0-25 points): website visits, content downloads, email opens
- Timing signals (0-20 points): recent funding, hiring surge, tech stack changes
- Fit quality (0-25 points): use case alignment, pain point match
</scoring_rubric>
For each lead:
1. Calculate a score (0-100) with reasoning
2. Classify as Hot (75+), Warm (50-74), or Cold (<50)
3. For Hot leads: draft a personalized 3-touch outreach sequence (email 1: value hook, email 2: social proof, email 3: direct ask)
4. For Warm leads: draft a nurture email
5. Flag any leads that need human review (incomplete data, conflicting signals)
Process the attached CSV and output results as a structured table plus the drafted emails.
You are a B2B sales ops expert. I'm uploading a CSV of our inbound leads. Score and qualify each one against our ICP, then draft outreach.
**Our Ideal Customer Profile:**
-...
You are a B2B sales ops expert. I'm uploading a CSV of our inbound leads. Score and qualify each one against our ICP, then draft outreach.
**Our Ideal Customer Profile:**
- Industries: [TARGET_INDUSTRIES]
- Company Size: [EMPLOYEE_RANGE]
- Decision Maker: [TITLES]
- Budget Range: [REVENUE_RANGE]
- Region: [REGIONS]
**Scoring Model (100 points total):**
- ICP Match: 30 pts (industry, size, role)
- Engagement: 25 pts (site visits, downloads, opens)
- Timing: 20 pts (funding, hiring, tech changes)
- Fit: 25 pts (use case, pain point alignment)
**For each lead, output:**
1. Score (0-100) + short reasoning
2. Tier: Hot (75+) / Warm (50-74) / Cold (<50)
3. Hot leads → 3-email outreach sequence (value hook → social proof → direct CTA)
4. Warm leads → 1 nurture email
5. Flag leads with missing data for human review
Use Code Interpreter to process the CSV. Output a summary table + full email drafts.
I have a CSV export of inbound leads I need scored and qualified. Please help me build a lead scoring system.
**My ideal customer:**
-...
I have a CSV export of inbound leads I need scored and qualified. Please help me build a lead scoring system.
**My ideal customer:**
- Industries: [TARGET_INDUSTRIES]
- Company size: [EMPLOYEE_RANGE]
- Decision makers: [TITLES]
- Budget signals: [REVENUE_RANGE]
- Geography: [REGIONS]
**Score each lead out of 100:**
- ICP alignment (30 pts)
- Engagement level (25 pts)
- Timing signals (20 pts)
- Use case fit (25 pts)
**Then:**
- Classify as Hot (75+), Warm (50-74), or Cold (under 50)
- Write a 3-email outreach sequence for Hot leads
- Write a single nurture email for Warm leads
- Flag any leads with incomplete data
I will paste/upload the lead data. Please output a scored table and all email drafts.
I need to score and qualify a list of sales leads from my CRM.
**Who we sell to (ideal customer):**
- Industries: [TARGET_INDUSTRIES]
- Company...
I need to score and qualify a list of sales leads from my CRM.
**Who we sell to (ideal customer):**
- Industries: [TARGET_INDUSTRIES]
- Company size: [EMPLOYEE_RANGE]
- Who we talk to: [TITLES]
- Budget range: [REVENUE_RANGE]
- Where: [REGIONS]
**How to score (out of 100):**
- Does the lead match our ideal customer? (30 points)
- How engaged are they with our content? (25 points)
- Are there buying signals like recent funding or hiring? (20 points)
- Do they have a use case we solve well? (25 points)
For each lead, give me: a score, a Hot/Warm/Cold label, and if they are Hot write a 3-email outreach sequence. For Warm leads, write one nurture email. Flag anything with missing info.
I will paste the lead data below.
Frequently Asked Questions
What does the AI-Powered Lead Qualification & Scoring prompt do?
Build an agentic workflow that ingests inbound leads from a CRM export, scores them against your ICP, drafts personalized outreach sequences, and flags high-priority leads for immediate follow-up.
Which AI models is this prompt tested on?
This prompt is field-tested on Claude, ChatGPT, Gemini and Copilot. Each model has its own optimized variant above.
Do I need a paid AI account to use this prompt?
No. This prompt is written to run on the free tier of Claude, ChatGPT, Gemini and Copilot. Paid tiers simply give you longer context windows and faster responses.
Can I customize this prompt for my business?
Yes. Any text inside square brackets is a placeholder you replace with your own business details, such as company name, audience, product or tone. You can also ask the AI to adjust format, length or style after the first output.
When was this prompt last verified?
Each model variant above shows its own freshness stamp. AlignAI re-verifies every prompt at least monthly and rebuilds when a major model changes.
Don’t see what you need? tailored to your use case.