User & JTBD Researcher

What it does

User & JTBD Researcher is a Cursor agent playbook named market-researcher. AgenticKit installs it so a session can adopt this role instead of acting as a generic coding assistant.

The market-researcher agent transforms raw customer feedback into product insights. It designs customer interview scripts, applies 'The Mom Test' methodology to avoid false validation, and clusters customer pain points into feature specs.

Conducts Jobs-To-Be-Done interviews, user feedback synthesis, and persona maps. User research specialist for Cursor that applies 'The Mom Test' and Jobs-To-Be-Done frameworks to extract real customer pain points.

Why it exists

A pile of agent files is not a team. market-researcher exists so one job, user & jtbd researcher, has a written brief, required skills, and a stop condition.

It ships in the Marketing Kit. Skills it must read: Jobs-To-Be-Done (JTBD) Customer Research; The Mom Test Customer Validation Framework; Win/Loss Analysis & Churn Diagnostics. Commands that adopt this role: /feature-spec: PRD & Product Feature Requirement Spec; /positioning: Product Positioning & ICP Strategic Framework; /define-brand-voice: Brand Voice & Style Guide Creator.

When to use it

• Validating new SaaS ideas before writing code
• Synthesizing customer support and cancellation feedback
• Discovering exact customer language for landing page copy

When not to use it

• Do not ask market-researcher 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/market-researcher is on disk.
2. Run /feature-spec: PRD & Product Feature Requirement Spec, or start a chat and tell Cursor to adopt the market-researcher role.
3. The agent should read: Jobs-To-Be-Done (JTBD) Customer Research; The Mom Test Customer Validation Framework; Win/Loss Analysis & Churn Diagnostics.
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 market-researcher. Validating new SaaS ideas before writing code. Read jtbd-interview before you edit."

Or let the pipeline invoke it: /feature-spec: PRD & Product Feature Requirement Spec.

Capabilities you should actually see: Jobs-To-Be-Done (JTBD) customer interview question design

Example output

• market-researcher should leave files or a written verdict, not a vibe check. Jobs-To-Be-Done (JTBD) customer interview question design 'The Mom Test' validation frameworks to uncover true intent
• Marketing agents write markdown under docs/marketing/ so later commands can reuse positioning and voice.

Best practices

• Jobs-To-Be-Done (JTBD) customer interview question design
• 'The Mom Test' validation frameworks to uncover true intent
• Customer feedback clustering and pain point synthesis
• User persona mapping with exact customer voice quotes
• One role per chat unless a command is explicitly orchestrating a sequence.

Common mistakes

• Using market-researcher 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.