# Turn product feedback into a decision list Designed for: Small teams deciding what to investigate before adding features Result: Grouped requests with customer references, reported problems and unanswered questions kept distinct. ## Try a sample first Illustrative example, not a recorded Bot run. This adaptation has not been runtime-tested. ### Complete first request Group feedback by the problem people are trying to solve. Keep source and customer IDs, distinguish duplicate reports from independent demand, and separate reported bugs from requested features. Propose the smallest useful investigation without inventing priority, revenue, customer commitments or a delivery date Use only the records I supply. Label missing or uncertain information. Do not connect accounts, browse, send, submit, publish, spend money or create a schedule. Return a draft for my review. Fictional feedback. F1, customer C1: 'CSV export is blank on my phone.' F2, customer C1: the same report forwarded by sales. F3, customer C2: 'Please add XLSX so our accountant can open the file.' F4, customer C3: 'We cannot find the existing CSV button.' No reproduction, browser details, revenue or promised dates are supplied. ### Example result Export failure: F1 and F2 are one customer's report, not two independent requests; reproduce on the reported device after obtaining browser details. Spreadsheet format: F3 requests XLSX; ask whether existing CSV meets the accountant's need before building. Findability: F4 concerns an existing button; check the navigation and instructions. Three distinct customers supplied four records. No bug is reproduced, feature approved or delivery date promised. ### Check the answer - Count three customers, not four independent votes. - Keep the reported failure separate from XLSX and findability. - Suggest investigations without claiming a verified bug or approved roadmap. Inspired by Grok Bot's Product Feedback Analyst use case: https://x.ai/bot/s9e2a2591b97ca74fbeaa Found through Grok Bot use cases (https://x.ai/bot/use-cases). This fictional sample was written by Bot Cabinet. ## Operating guide - **When to use it:** Use this workflow when you need grouped requests with customer references, reported problems and unanswered questions kept distinct. - **Lead Bot:** Nova - **Cadence:** When a person supplies the approved brief and starts the workflow - **Typical first run:** 15–30 minutes for a first manual run ### Access for the first run - The approved inputs listed on this page - Only the files, sources, and services required for this run - No sending, publishing, spending, or live-system changes without approval ## Recommended starting Bot 1. Nova Use Nova with the task below. This is a workflow for an existing role, not a separate installed Bot. ## Information to gather - Start with the fictional records below - For your own task, choose only the records you want the Bot to use - Remove private details you do not need for the task ## Workflow ### 1. Nova Group feedback by the problem people are trying to solve. Keep source and customer IDs, distinguish duplicate reports from independent demand, and separate reported bugs from requested features. Propose the smallest useful investigation without inventing priority, revenue, customer commitments or a delivery date Output: Grouped requests with customer references, reported problems and unanswered questions kept distinct. Message to send: Use the approved inputs I provide. Group feedback by the problem people are trying to solve. Keep source and customer IDs, distinguish duplicate reports from independent demand, and separate reported bugs from requested features. Propose the smallest useful investigation without inventing priority, revenue, customer commitments or a delivery date. Return this result: Grouped requests with customer references, reported problems and unanswered questions kept distinct.. Ask me about missing information before you continue. ## Overall request Group feedback by the problem people are trying to solve. Keep source and customer IDs, distinguish duplicate reports from independent demand, and separate reported bugs from requested features. Propose the smallest useful investigation without inventing priority, revenue, customer commitments or a delivery date Use only the records I supply. Label missing or uncertain information. Do not connect accounts, browse, send, submit, publish, spend money or create a schedule. Return a draft for my review. ## Decisions for a person - Check the result against the supplied records - Approve any account connection, schedule or outside action separately - Review anything before it is sent, submitted, purchased or published ## First test Count three customers, not four independent votes. Keep the reported failure separate from XLSX and findability. Suggest investigations without claiming a verified bug or approved roadmap. ## Success checkpoint Check the result against your original material. You make the decisions listed below. Count three customers, not four independent votes. Keep the reported failure separate from XLSX and findability. Suggest investigations without claiming a verified bug or approved roadmap. ## If the workflow stalls If the result is incomplete, mark the missing information and ask the same Bot to correct it. Add another Bot only when a genuinely separate role or independent check would help. ## Hermes Desktop setup 1. Open the linked Bot's page, download its .tar.gz profile, and import it from the Profiles screen in Hermes Desktop. 2. Review the profile's SOUL.md, Bot Passport, and requested access. 3. Run the complete request in that Bot's chat with low-risk material and review the result. 4. Add a schedule, outside connection, or optional specialist only after the manual version works.