Evermuse
    HomeFeaturesMCPPricingContact
    Prompt Library

    23 prompts that put your customers in the chat.

    Copy a prompt, paste it into Claude, Cursor, or ChatGPT, and get an answer grounded in what your customers actually said. Each one runs on the Evermuse MCP.

    New here? Connect the MCP, then send your first prompt
    Setup steps for your client
    1. Add this MCP URL
    2. Send this prompt

    23 prompts shown

    Hear what customers actually said

    Search every call, interview, email, and document in your workspace, and get answers tied to real quotes.

    What customers say about a topic

    Best for: Product managers, founders

    What are customers saying about [onboarding friction]? Pull the strongest quotes and link each one to the meeting or document it came from.
    • search
    • read_source

    Recap a single conversation

    Best for: Sales, customer success

    Summarize my last call with [customer]. List their needs, their pain points, and anything we said we would follow up on, with citations.
    • find_sources
    • summarize_conversation

    Top pain points for a segment

    Best for: UX researchers, product managers

    What are the top five pain points for [enterprise] customers? For each one, give me two direct quotes and the conversation they came from.
    • search
    • view_item

    Every mention in a time window

    Best for: Product managers, UX researchers

    Find every conversation from the last 90 days where a customer brought up [SSO]. Group them by theme and tell me which themes come up most.
    • search
    • find_sources
    • read_source

    Pressure-test a hunch

    Best for: Founders, product leaders

    I believe [small teams churn because setup takes too long]. Search our customer evidence for anything that supports or contradicts this, and tell me how strong the case really is.
    • search
    • read_source

    Write PRDs, specs, and briefs with evidence

    Run research and writing workflows where every requirement links back to a customer.

    PRD grounded in customer requests

    Best for: Product managers

    Write a PRD for [bulk export], grounded in what customers have asked for. Every requirement should link back to a real customer quote.
    • find_skills
    • read_skills
    • create_prd
    • search

    Customer context before you code

    Best for: Engineers in Cursor or Claude Code

    Before I build [saved filters], pull the customer context behind it: who asked for it, what problem they are solving, and the edge cases they mentioned. Then write a feature spec I can implement from.
    • search
    • write_feature_spec

    User stories with acceptance criteria

    Best for: Product managers, engineers

    Turn the plan for [team workspaces] into user stories with acceptance criteria. Cite the customer evidence behind each story.
    • user_stories
    • search

    Answer a research question

    Best for: UX researchers

    Run customer research on this question: why do [trial users] stop before [inviting a teammate]? Show me the evidence for each finding.
    • customer_research
    • search

    Personas from real interviews

    Best for: UX researchers, designers

    Build user personas from our interviews with [mid-market admins]. Base every goal and frustration on something a customer said, and cite it.
    • user_personas
    • search

    Weekly customer brief

    Best for: Product leaders, founders

    Write a one-page brief on what we learned from customers this week: new needs, recurring pain points, and the quotes worth sharing with the team.
    • write_brief
    • find_sources

    Know your product and your competitors

    Load your product context, size up competitors, and check both against what customers say.

    Load your product context

    Best for: Anyone starting a new chat

    Load our product context and play it back to me: mission, segments, personas, features, and current projects. Flag anything that looks out of date.
    • get_products
    • get_product_summary
    • get_projects

    Where a competitor beats you

    Best for: Product leaders, product marketing

    Where are we most exposed to [our top competitor], and what do customers say about it?
    • competitor_analysis
    • search

    Capability comparison

    Best for: Product managers, sales

    List our competitors and compare their [reporting] capabilities with ours. Where do customers tell us we are behind?
    • list_competitors
    • get_competitor_capabilities
    • search

    Find differentiation openings

    Best for: Founders, product leaders

    Which things are customers asking for that none of our competitors do well? Rank them by how often they come up.
    • competitor_analysis
    • get_competitor_capabilities
    • search

    Turn opportunities into shaped work

    Review the opportunities Evermuse surfaces, then create and update shaping notes from the conversation.

    Review the top opportunities

    Best for: Product managers, product leaders

    Show me the top product opportunities Evermuse has surfaced. Rank them by strength of customer evidence and tell me which one you would shape first, and why.
    • get_opportunities

    Check shaping work in flight

    Best for: Product leaders

    Which shaping notes are still in the PRD stage? Summarize where each one stands and what is blocking it.
    • get_shaping_notes
    • read_shaping_note

    Opportunity to shaping note

    Best for: Product managers

    Turn the top [onboarding] opportunity into a new shaping note with the problem, the supporting evidence, and the open questions.
    • get_opportunities
    • create_shaping_note

    Update a note with new learning

    Best for: Product managers

    Update the shaping note for [bulk export] with what we learned from this week’s customer calls.
    • read_shaping_note
    • search
    • update_shaping_note

    File new evidence without leaving the chat

    Save transcripts and notes to the right project, and record or correct the signals in them.

    File a transcript

    Best for: Sales, customer success

    Save this transcript to the [Q2 discovery] project and log the pricing pushback as a pain point.
    • add_source
    • add_signals

    Turn call notes into signals

    Best for: Anyone who talks to customers

    Here are my notes from today’s call with [customer]. Add them to the [onboarding research] project and record the needs and quotes as signals.
    • add_source
    • add_signals

    Correct a signal

    Best for: UX researchers

    The signal about [export limits] is recorded as feedback, but it is really a pain point. Correct it.
    • search
    • update_signals

    Draft a custom signal type

    Best for: Research ops, product ops

    Draft a custom signal type called [churn risk] for moments when a customer hints they might leave. I will review and approve it in Evermuse.
    • create_signal_type

    Replace anything in [square brackets] with your own feature, customer, segment, or project. The tool names under each prompt are the Evermuse MCP tools your assistant typically calls. You never have to type them.

    How to get better answers

    Four habits that make any prompt on this page work harder.

    1. 1

      Name the segment and the time range

      “Enterprise customers in the last 90 days” gets a sharper answer than “customers”. The narrower the question, the more relevant the evidence.

    2. 2

      Ask for the source

      Add “with citations” or “link each quote to its meeting”. Your assistant will show which conversation backs each claim, so you can check it yourself.

    3. 3

      Say what you want to make

      Ask for a PRD, a feature spec, user stories, personas, or a brief by name. Your assistant loads the matching Evermuse skill and follows its template and checklist.

    4. 4

      Chain prompts in one chat

      Start with the evidence, then ask for the spec, then file a shaping note. Each step builds on what the assistant already pulled.

    Questions about the prompt library

    A prompt is only as good as the evidence behind it.

    Sign up for Evermuse, connect the MCP to the assistant you already use, and run your first prompt against your own customer conversations.

    Evermuse
    Monitored by Drata - SOC 2
    Sensiba - SOC 2 Type 2 certified
    GDPR Ready

    Solutions

    • By role
      • For AI Ops
      • For Product Ops
      • For Product Managers
      • For Product Leaders
      • For UX Researchers
      • For Designers
      • For Research Ops
      • For Developers
      • For Sales & CS
      • For Product Marketing
    • By industry
      • Software & SaaS
      • Fintech & Financial Services
      • E-Commerce & Marketplaces
      • Agencies & Consultancies
      • Logistics & Supply Chain
      • HR & Payroll
      • Insurance
      • Real Estate
      • Education & Non-Profits
    • By company size
      • Start-ups
      • Scale-ups
      • Enterprise
    • Use Cases

    Compare

    • vs. AI(e.g., Claude)
      • vs. Generic AI
      • vs. Claude
      • vs. ChatGPT
      • vs. Gemini
      • vs. Microsoft Copilot
    • vs. Doc Repos(e.g., Notion)
      • vs. Notion
      • vs. Glean
    • vs. Research Tools(e.g., Dovetail)
      • vs. Dovetail
      • vs. Productboard
      • vs. Sprig
      • vs. BuildBetter
      • vs. Condens
      • vs. Marvin
      • vs. Enterpret
      • vs. Canny
      • vs. Pendo
      • vs. Maze
      • vs. Aha!
      • vs. Dscout
    • vs. Call Recorders(e.g., Gong)
      • vs. Gong
      • vs. Fireflies
      • vs. Read AI
      • vs. Fathom
      • vs. Granola
      • vs. Otter.ai

    Get Started

    • Book a UXR Demo
    • Book a Developer Demo
    • Book a Product Manager Demo
    • Contact Sales

    Product

    • Get Started
    • How It Works
    • Features
    • Pricing
    • Integrations
    • MCP
    • Developer Docs
    • Prompt Library
    • Changelog
    • Roadmap
    • Resources
    • Webinars
    • Guides

    Company

    • About
    • Careers
    • Blog
    • Community
    • Press
    • Partner Program
    • Contact
    • Media Kit
    • Workshops
    • AI Research Agency

    Support

    • Help Center
    • FAQ
    • System Status
    • Report a Bug
    • Security & Trust
    • Privacy Policy

    © 2026 Usermuse, Inc. All rights reserved.

    ·Sitemap