| Rank | Lead | Score | Rationale | Action |
|------|------|-------|-----------|--------|
| 1 | Operations Manager, GrowthCo, 120 employees | 9/10 | Perfect size fit, ops title matches ICP exactly, likely budget authority | Contact Now |
| 2 | Head of Operations, Acme Logistics, 300 employees | 8/10 | Strong fit on size and title, logistics vertical has clear ops pain points | Contact Now |
| 3 | IT Director, RegionalBank, 400 employees | 5/10 | Right size but IT title suggests indirect buyer, banking may have long procurement cycles | Nurture |
| 4 | VP of Finance, MegaCorp, 10,000 employees | 3/10 | Company too large for ICP, finance title misaligned with ops tool | Skip |
| 5 | CEO, TinyStartup, 8 employees | 2/10 | Company far too small, unlikely to have budget or ops complexity to justify tool | Skip |

Summary  
This chapter covers how to structure input data and craft prompts for an AI model to automatically assign and update scores and rankings to items based on specified attributes.

General domain of usage  
Sales lead scoring

To start scoring a lead list with AI, you first need a sample list of leads with attributes that influence buying decisions. Prepare a spreadsheet or table containing columns such as **company name**, **contact name**, **industry**, **company size**, **annual revenue**, **job title**, **location**, and **previous engagement score**. These attributes provide context for AI models to evaluate and rank leads based on their likelihood to convert. Make sure your list includes a mix of companies and contacts to reflect real-world diversity, as this will help you see how AI can differentiate between high- and low-potential leads.

**AI scoring is not a one-time process.** As new data becomes available—such as recent interactions, updated company news, or changes in contact roles—AI models can automatically adjust lead scores. This continuous updating ensures your pipeline always reflects the latest information, helping you focus on leads that are most likely to convert at any given moment. By automating score updates, you eliminate manual guesswork and react quickly to evolving opportunities, keeping your sales process agile and data-driven.

## Task
Paste a list of 5–10 prospects and let Claude rank them for you.

Send this message to Claude in the lab on the right:

> **Score these leads for a B2B SaaS tool aimed at ops teams at 50–500 person companies:**
>
> 1. Head of Operations, Acme Logistics, 300 employees
> 2. CEO, TinyStartup, 8 employees
> 3. VP of Finance, MegaCorp, 10,000 employees
> 4. Operations Manager, GrowthCo, 120 employees
> 5. IT Director, RegionalBank, 400 employees

- Review Claude's scores and rationale for each lead
- Try swapping in leads from your own pipeline
- Ask Claude to re-score if you disagree with a verdict

Done when you understand how the scoring logic works.

Master the modern B2B sales pipeline by leveraging AI at every stage - from identifying prospects to closing deals. This hands-on lab course guides you through mapping pipelines, scoring leads, crafting outreach, and using AI as your sales co-pilot.

Explore the fundamentals of sales pipelines and how AI is revolutionizing B2B sales processes, from pipeline mapping to interpreting buying signals.

Learn how to use AI to source, score, and qualify leads, transforming raw contact lists into actionable opportunities.

Master AI-powered techniques for crafting cold emails, follow-ups, and LinkedIn messages that drive engagement and meetings.

Leverage AI to prepare for calls, handle objections, and draft winning proposals, accelerating deals from negotiation to close.