Customer Proof Marketer

What it does

Customer Proof Marketer is a Cursor agent playbook named customer-marketer. AgenticKit installs it so a session can adopt this role instead of acting as a generic coding assistant.

The customer-marketer agent turns one customer into a before/after story you can put on the landing page. content-marketer writes SEO blogs. This role only uses named or explicitly approved quotes.

One real customer. Before, after, quote. No fiction. Builds case studies and testimonial blocks from real quotes. Marks [NEEDS QUOTE] instead of inventing proof.

Why it exists

A pile of agent files is not a team. customer-marketer exists so one job, customer proof marketer, has a written brief, required skills, and a stop condition.

It ships in the Marketing Kit. Skills it must read: Customer Case Study Narrative; Win/Loss Analysis & Churn Diagnostics; Marketing Deliverable Auto-Save & Repo Sync. Commands that adopt this role: /case-study: One-Customer Proof Story; /landing-page: High-Converting Landing Page Copy Architect; /whats-new: Ship-to-Customer Narrative.

When to use it

• Landing page with zero proof
• A happy user you have not written up
• Sales needs one story, not a blog post

When not to use it

• Do not ask customer-marketer to do a different role's job. If you need a migration, switch agents.
• Do not keep the same chat after this agent has finished its artifact. Start a reviewer in a new thread.
• Do not invoke every agent in the kit for a small change.

Example workflow

1. Install the Marketing Kit so .cursor/agents/customer-marketer is on disk.
2. Run /case-study: One-Customer Proof Story, or start a chat and tell Cursor to adopt the customer-marketer role.
3. The agent should read: Customer Case Study Narrative; Win/Loss Analysis & Churn Diagnostics; Marketing Deliverable Auto-Save & Repo Sync.
4. It produces the artifact for this role only, then stops.
5. A different agent or you review. Same-chat self-review is not a review.

Example usage

Example: "You are customer-marketer. Landing page with zero proof. Read case-study-narrative before you edit."

Or let the pipeline invoke it: /case-study: One-Customer Proof Story.

Capabilities you should actually see: Interview or email ask for a quote

Example output

• customer-marketer should leave files or a written verdict, not a vibe check. Interview or email ask for a quote Before/after narrative with cited metrics only
• Marketing agents write markdown under docs/marketing/ so later commands can reuse positioning and voice.

Best practices

• Interview or email ask for a quote
• Before/after narrative with cited metrics only
• Landing-ready pull quotes
• Placeholder discipline when proof is missing
• One role per chat unless a command is explicitly orchestrating a sequence.

Common mistakes

• Using customer-marketer as a synonym for 'the Cursor agent'. It is a brief, not the product.
• Skipping the required skills and hoping the role name is enough.
• Publishing the first draft of launch copy without a human edit.
• Invoking this agent and three unrelated ones in the same prompt.