Summary  
This chapter covers modeling a multi-stage pipeline using structured data (e.g., lists of dictionaries or DataFrames) and applying prompt engineering to invoke AI-driven recommendations for advancing items through each stage.  

General domain of usage  
Sales pipeline management

To map your first sales pipeline with **AI**, start by laying out the key stages that every deal will pass through. A typical sales pipeline consists of stages such as **"Lead Identified," "Contacted," "Qualified," "Proposal Sent,"** and **"Closed."** Use **structured data** to represent these stages and the deals within them. In Python, you can use a list of dictionaries or a simple `DataFrame` to organize deals, their attributes, and their current stage. Each deal might include fields like **company name, contact, deal value, stage,** and **notes**.

Begin by creating a small set of sample deals, each at a different stage. This helps you visualize the flow of opportunities and track where each prospect is in your process. By structuring your data, you set the foundation for **AI-driven recommendations** and automation.

Next, incorporate **prompt engineering** to guide AI in making decisions or suggesting actions. For example, you can frame a prompt such as: `Given a deal at the 'Qualified' stage with high engagement but no recent contact, what should the next step be?` This approach allows AI to interpret the context and recommend targeted actions.

Once your pipeline is mapped and your prompts are clear, you can simulate AI-driven updates. For instance, based on deal activity and stage, the AI can suggest sending a follow-up email, scheduling a call, or moving the deal to the next stage. This workflow not only streamlines your process but also ensures that no opportunity falls through the cracks.

Mapping your pipeline with structured data and prompt engineering transforms your sales process from reactive to proactive, letting AI surface the best next steps for every deal.

**AI brings intelligence to your pipeline by analyzing deal data and context to recommend the next best action for each opportunity.** By tracking deal stages, recent activities, engagement levels, and deal values, AI can prioritize deals that need attention and suggest actions that increase the chance of closing.

For example, if a deal has stalled at the `Proposal Sent` stage, AI might recommend a follow-up call or a personalized email. If a new lead has just been qualified, the AI could suggest scheduling a discovery call or sharing relevant case studies. These recommendations are based on patterns in the data and prompt responses designed to move deals forward efficiently.

By leveraging AI recommendations, you maximize your chances of closing deals and ensure a consistent, data-driven approach to sales. The more structured your pipeline data and prompts, the more effective your AI-driven sales process will be.

## Task
Tell Claude what you sell and who your customer is, then let it guide you to name your 5 pipeline stages.

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

> **I sell [your product]. My typical customer is [describe them]. Help me map out my pipeline.**

As Claude asks questions, answer honestly — even rough answers work fine.

- Name each stage in your own words
- Confirm the order makes sense for your sales cycle
- Ask Claude to adjust any stage that doesn't fit

Done when you have a 5-stage pipeline you'd actually use.
Nothing to submit — just hit **Next chapter**.

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.