Grouped requests with customer references, reported problems and unanswered questions kept distinct.
Designed for: Small teams deciding what to investigate before adding features
Illustrative example, not a recorded Bot run. This sample was written to explain the task; your Bot's answer needs checking.
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.
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 answerAlready have an assistant? Copy the sample task into its chat. For a continuing role, review Nova's instructions and limits first.
These are setup guides, not automatic imports. Available tools and account access differ by app.Inspired by Grok Bot's Product Feedback Analyst use case , found through Grok Bot use cases. The sample above is Bot Cabinet's own fictional example.
Source idea; this adaptation has not been runtime-tested.
Use one Bot for the first run. Add a specialist only when the job becomes complicated enough to need a separate role, different access, or independent review.
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
Produces: Grouped requests with customer references, reported problems and unanswered questions kept distinct.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.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.
Use this as the complete first-run request.
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.
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 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.