Identify Your Ideal Client with AI: Method and Prompts

🎯 Introduction: Without an Ideal Client, AI Amplifies Noise

90% of prospecting campaigns fail for one reason: the target is too broad. "SMBs in France," "marketing directors," "SaaS startups"... These are not targets — they are oceans. And when you feed AI a vague target, it generates massive vagueness — thousands of leads that will never convert.

The alternative? Build a precise ICP (Ideal Customer Profile), then use AI to identify the exact companies and people that match. A well-defined ICP transforms a 2% conversion rate into 15-25%.

In this article, we cover how to build your ICP with AI in 4 steps, with ready-to-use prompts and concrete tools to go from theory to a prospect list.

📋 Table of Contents

1. What Is an ICP (and Why It Matters)
2. The 4 Components of an ICP in 2026
3. 5 AI Prompts to Build Your ICP
4. Identify Intent Signals with AI
5. Turn Your ICP into a Prospect List
6. Score and Prioritize with AI
7. Fatal Mistakes When Defining Your ICP

1. What Is an ICP (and Why It Matters)

Definition

The ICP (Ideal Customer Profile) is a precise, data-driven description of your ideal client. Not a marketing persona with a name and a stock photo — an operational description that guides your prospecting actions.

ICP vs. Persona: The Difference

• ICP: description of the ideal company (industry, size, revenue, tech stack)
• Persona: description of the ideal person (role, motivations, frustrations, buying journey)
• You need both: the ICP to target the right companies, the persona to speak to the right people

Impact on Conversion

💡 Pareto's Law applied: 20% of your clients generate 80% of your revenue. Your ICP is the description of those 20%.

2. The 4 Components of an ICP in 2026

In 2026, an ICP based solely on firmographics (industry + size) is no longer enough. Here are the 4 components of a modern ICP:

1. Firmographics

Company characteristics:
- Industry (NAF code or SIC code)
- Size: headcount, revenue, number of locations
- Location: country, region, city
- Status: startup, SMB, mid-market, enterprise
- Company age

2. Technographics

Tools and technologies in use:
- Tech stack (for B2B SaaS)
- Marketing tools (HubSpot, Mailchimp, Salesforce...)
- Cloud infrastructure (AWS, GCP, Azure)
- CMS (WordPress, Shopify, custom...)

💡 Why it matters: if you sell an AWS → GCP migration tool, targeting companies on AWS is 10x more effective than targeting "tech SMBs."

3. Buying Behavior

Signals indicating a need:
- Budget allocated to your product category
- Buying process (who decides, how long)
- Purchase frequency (subscription, one-time, renewal)
- Price sensitivity vs. value sensitivity

4. Intent Signals

Behaviors indicating they are currently in-market:
- Hiring in a key department
- Recently raised funding
- Blog post or LinkedIn post on a topic related to your offering
- Visit to your website (via tools like Clearbit, 6sense)
- Searching for keywords related to your solution

⚠️ Intent signals are the most powerful component in 2026. A company hiring a "Head of Data" is likely building a data infrastructure — that's the best time to reach out if you sell data services.

3. 5 AI Prompts to Build Your ICP

Here are 5 prompts to use in Claude or ChatGPT to build your ICP step by step.

Prompt 1: Analyze Your Best Existing Clients

I will give you the list of my 10 best clients (those generating the most revenue and most satisfied). For each, I provide: industry, size (headcount and revenue), contact's role, problem solved, price paid.

From these data, identify the common patterns and propose an ICP in 3 parts:
1. Firmographics (must-have + nice-to-have criteria)
2. Decision-maker persona (role, motivations, frustrations)
3. Intent signals to watch

My clients:
PH_liste_clients_PH

Why it works: your best existing clients are the best data source for your ICP. AI identifies patterns you can't see.

Prompt 2: Define Qualification Criteria

My offering: PH_votre_offre_PH
Price: PH_prix_PH
Sales cycle: PH_cycle_de_vente_PH

Define the BANT criteria (Budget, Authority, Need, Timeline) to qualify a prospect.
For each criterion, provide:
- The question to ask
- The ideal answer (green flag)
- The acceptable answer (yellow flag)
- The disqualifying answer (red flag)

Why it works: the BANT framework is classic but AI adapts it precisely to your offering instead of staying generic.

Prompt 3: Identify Specific Intent Signals

For a company selling PH_votre_offre_PH to PH_votre_cible_PH, what are the 10 most predictive intent signals of an imminent purchase?

Rank them by relevance (1 = strongest) and for each:
- Where to detect it (LinkedIn, website, directory, press...)
- How to verify it automatically
- Recommended action timeline (upon detection, within 24h, within 1 week)

Why it works: AI cross-references thousands of B2B sales patterns to identify the signals most correlated with a purchase.

Prompt 4: Create the Decision-Maker Persona

Based on the following ICP: PH_icp_PH

Create a detailed persona of the decision-maker including:
- Typical profile (role, age, career path)
- Their 3 biggest frustrations at work
- What they read (blogs, newsletters, LinkedIn)
- How they make buying decisions
- The most common objections and how to address them
- A "day in the life" of this persona

Why it works: a detailed persona lets you craft messages that truly resonate, instead of speaking to a generic profile.

Prompt 5: Validate and Refine the ICP

Here is my current ICP: PH_icp_PH
Here are my 5 most recent lost prospects: PH_prospects_perdus_PH

Analyze why these prospects didn't convert and suggest:
1. Which criteria in my ICP were poorly calibrated
2. Which criteria were missing
3. The revised ICP version 2

Why it works: an ICP isn't set in stone. Lost deal analysis is the best way to continuously refine it.

4. Identify Intent Signals with AI

Intent Signal Sources

Automate Detection with Clay.com

Clay.com is the most powerful tool for automating intent signal detection. Here's how:

1. Import a list of target accounts (1,000+ companies)

2. Clay enrichment:
   - Company's latest LinkedIn posts
   - Recent hires (via LinkedIn + Indeed)
   - Funding rounds (via Crunchbase)
   - Tech stack (via BuiltWith)
   - Recent news (via Google News API)

3. AI intent scoring:
   - Clay analyzes enriched data
   - Each company receives a 1-100 score
   - Based on the presence of your intent signals

4. Filter "hot leads" (score > 70):
   - These companies are currently in-market
   - Prioritize outreach toward them

Scoring Prompt for Clay

You are a sales analyst. Evaluate the purchase intent score (1-100) for this company.

Data:
- Company: PH_company_PH
- Industry: PH_industry_PH
- Headcount: PH_employees_PH
- Recent hires: PH_recent_hires_PH
- Latest news: PH_recent_news_PH
- Tech stack: PH_tech_stack_PH
- Latest LinkedIn post: PH_latest_post_PH

Signals to look for:
PH_intent_signals_PH

Respond in JSON: {"score": int, "signals_found": [str], "recommendation": str}

"Hot" threshold = 70+

5. Turn Your ICP into a Prospect List

Once the ICP is defined, you need to find the matching companies and people.

Step 1: List Target Accounts

Use your ICP as a filter on the following sources:

• LinkedIn Sales Navigator: advanced filters (industry, size, location, growth)
• Apollo.io: database of 275M+ contacts with detailed filters
• Crunchbase: for startups (funding, growth stage)
• Google Maps (via Apify): for local businesses

Step 2: Find Decision-Makers

For each targeted account, identify the right people:

• Hunter.io: Domain Search → email list per company
• Prospeo.io: LinkedIn Scraper → profiles matching your persona
• Phantombuster: automated extraction from LinkedIn Sales Navigator

Step 3: Enrich and Score

import pandas as pd

# Enrichment pipeline
prospects = pd.read_csv('raw_prospects.csv')

# 1. Verify emails with Prospeo or Hunter
# (see previous sections for API details)

# 2. ICP scoring function
def analyze_icp_fit(prospect: dict, icp: dict) -> int:
    \"\"\"Score a prospect from 0 to 10 based on ICP match.

    Args:
        prospect: dict with keys sector, size, tech_stack, region
        icp: dict with keys sectors[], size_range, tech_required[], regions[]

    Returns:
        Score from 0 (no match) to 10 (perfect fit)
    \"\"\"
    score = 0

    # Firmographics (4 pts max)
    if prospect.get('sector') in icp.get('sectors', []):
        score += 2
    if icp['size_range'][0] <= prospect.get('size', 0) <= icp['size_range'][1]:
        score += 2

    # Technographics (3 pts max)
    required = set(icp.get('tech_required', []))
    prospect_tech = set(prospect.get('tech_stack', '').split(','))
    matches = len(required & prospect_tech)
    score += min(matches, 3)

    # Location (3 pts max)
    if prospect.get('region') in icp.get('regions', []):
        score += 3

    return score

# 3. Score all prospects
icp_criteria = {
    'sectors': ['SaaS', 'FinTech'],
    'size_range': (20, 200),
    'tech_required': ['HubSpot', 'AWS'],
    'regions': ['Île-de-France', 'Lyon']
}

for idx, prospect in prospects.iterrows():
    prospects.loc[idx, 'icp_score'] = analyze_icp_fit(
        prospect.to_dict(), icp_criteria
    )

# 4. Filter and prioritize
hot_leads = prospects[prospects['icp_score'] >= 7]
warm_leads = prospects[(prospects['icp_score'] >= 4) & (prospects['icp_score'] < 7)]

print(f"Hot leads: {len(hot_leads)}")
print(f"Warm leads: {len(warm_leads)}")

6. Score and Prioritize with AI

The Scoring Model

A good scoring combines 3 dimensions:

Multi-Dimensional Scoring Prompt

Evaluate this prospect on 3 dimensions (1-10 each):

Prospect: PH_first_name_PH PH_last_name_PH, PH_job_title_PH at PH_company_PH

Target ICP: PH_icp_PH

Available data:
- Headcount: PH_employees_PH
- Estimated revenue: PH_revenue_PH
- Tech stack: PH_tech_stack_PH
- Recent hires: PH_hires_PH
- Visited our site: PH_visited_site_PH
- Opened our emails: PH_opened_emails_PH

Respond in JSON:
{
"fit_score": int,
"intent_score": int,
"engagement_score": int,
"total_score": int,
"priority": "hot", "warm", or "cold",
"next_action": str
}

Hot = total >= 24, Warm = total >= 15, Cold = total < 15

Automate Scoring with Clay

Clay.com lets you automatically score each prospect on import. Configure your scoring model once, and every new entry is evaluated automatically. Result: your pipeline sorts itself, and you spend your time on hot leads.

7. Fatal Mistakes When Defining Your ICP

❌ Targeting Too Broad

"SMBs in France" = 4 million companies. "SaaS SMBs with 20-50 employees in Île-de-France using HubSpot" = a few thousand. The more precise the ICP, the higher your conversion rate.

❌ Relying Only on Assumptions

"My ideal client is a tech startup CEO" — really? Do your data confirm this? Always validate your ICP with data from your existing clients (see Prompt 1).

❌ Ignoring Intent Signals

A static ICP (firmographics only) tells you WHO to target. Intent signals tell you WHEN to contact them. Without signals, you reach out to companies with no current need — and you waste your time.

❌ Not Refining the ICP Regularly

Your clients evolve, your offering evolves, the market evolves. An ICP set once loses relevance in 3-6 months. Revise it quarterly.

❌ Confusing ICP with TAM (Total Addressable Market)

The ICP is not your total market. It's your priority target. You can expand later, but start with a narrow, well-defined target.

✅ Conclusion

Building a precise ICP isn't optional — it's the foundation of any prospecting that converts. AI accelerates every phase: analyzing your existing clients, identifying intent signals, scoring prospects.

To summarize the process:
1. Prompts 1-2: build your ICP from your best clients
2. Prompts 3-4: identify intent signals and create the decision-maker persona
3. Prompt 5: continuously refine with lost prospects
4. Tools: Hunter.io, Prospeo.io and Phantombuster to build your list
5. Scoring: prioritize with the 3-dimension model (Fit 40% / Intent 40% / Engagement 20%)

Next step: now that you know WHO to target and WHEN to contact them, discover how to automate lead collection and write personalized LinkedIn messages with AI.

Your ICP evolves with your market. Revise it every quarter to stay relevant.

📚 Related Articles

• How to Automate Lead Collection with AI: Complete Guide 2026: once the ICP is defined, collect leads automatically
• AI LinkedIn Outreach: 10 Prompts for Personalized Messages: reach out to your identified prospects with AI-powered messages
• 7 AI Tools That Saved Me €300/month (No Coding): the tools to automate your prospecting