Summary  
This chapter illustrates how structured prompting—supplying specific context and details—leads to more relevant AI-generated recommendations than generic, high-level queries.

General domain of usage  
Evaluating and renewing a software service contract.

Your Head of Marketing forwards you an email: 
> <b>HubSpot renewal is due in three weeks — $48K for the year. Do we renew, renegotiate, or look elsewhere?

You open Claude and ask. You get back a reasonable-sounding take. Problem is, it doesn't know how much of HubSpot you're actually using, what happened the last time this came up for renewal, or what else is out there at this price point.



## Step 1 — Ask It Straight

> <b>Should we renew our HubSpot contract?

Generic answer: HubSpot is solid but pricey, some companies switch to cheaper tools as they scale. True of literally any CRM renewal, useless for yours.



## Step 2 — Give It the Real Situation

> <b>We're a 60-person company paying $48,000/year for HubSpot's Marketing Hub Professional. Marketing uses it daily for email and landing pages, but sales barely touches the CRM side and mostly works out of spreadsheets anyway. We renewed at a discount last year after threatening to leave. Give me a straight recommendation: renew, renegotiate, or switch. Argue the strongest case against your own recommendation, and tell me what you'd need to know that I haven't told you.



> ## Task
> Run both steps and compare them. Did the structured version pick up on the fact that sales barely uses half the platform, or ask about contract lock-in and what switching would actually cost?

Master the skills needed to build reliable AI decision systems with Claude, tackling real business calls like switching tools, approving a hire, and renewing a vendor contract. Progress from prompt-only reasoning to tool-grounded analysis with live data, then package your approach into a reusable Claude agent with structured output and a no-invented-facts constraint. By the end, you'll write a full agent system prompt from scratch.

Discover how to build an AI decision system for a real tool-switch call. Start with prompt-only reasoning, ground it in live pricing and migration data via web search, then build a Tool Switch Advisor agent that routes tasks and cites its sources.

Explore the essentials of contextual prompting for hiring decisions. Compare a bare prompt to a context-rich one, analyze real team capacity data to test the case for a hire, then build a Hiring Decision Advisor agent around that data.

Dive into the fundamentals of building a Claude agent for a vendor renewal decision. Combine past notes, usage data, and market research into one recommendation, then write your own agent prompt with tool routing and a no-invented-facts rule.