Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for product managers

Customer Feedback to Product Request Agent

Send product a monthly ranked list of customer requests with revenue at stake

Customer Feedback to Product Request Agent: what goes in, what the agent does and what you get

What it does

Sales hears what buyers need, but the requests sit in call notes and emails where product teams never see them. Each month this agent reads deal notes, lost-deal reasons from the last two quarters and call transcripts. It pulls out each product request with the account and deal value, then matches it to the existing product request list. If a request cannot be matched with confidence, it groups similar ones and asks a sales manager to confirm the wording. It ranks requests by revenue at stake and number of accounts, and a request needs at least three accounts to enter the main list. Single-account requests above $250,000 are shown separately. The sales leader approves the list before it goes to product. Edge case: one large prospect's request is shown separately so it does not dominate the ranking.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedNo 1 STARTS WHEN Monthly product sync approaching 2 USES A TOOL Read notes, transcripts and lost reasons from thepast month 3 DOES Extract each product request with the account anddeal value 4 USES A TOOL Match requests to the existing product request list 5 CHECKS THE RESULT Did each request match an existing item withconfidence? If not: group similar unmatched requests and ask amanager to confirm wording. Back to step 3. 6 DOES Rank requests by revenue at stake and number ofaccounts 7 YOU APPROVE Sales leader approves the list sent to product 8 RESULT Ranked request list delivered
Read the steps as a list
  1. Monthly product sync approaching
  2. Read notes, transcripts and lost reasons from the past month
  3. Extract each product request with the account and deal value
  4. Match requests to the existing product request list
  5. Did each request match an existing item with confidence?If not: group similar unmatched requests and ask a manager to confirm wording. Back to step 3.
  6. Rank requests by revenue at stake and number of accounts
  7. Sales leader approves the list sent to productThe agent waits here for your OK.
  8. Ranked request list delivered

How it decides

Requests are ranked by total pipeline and lost revenue that mentioned them, with a minimum of three separate accounts to enter the main list.

  • Main list requires at least three accounts
  • Show single-account requests above 250k separately
  • Include lost deals only from the last two quarters

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Minimum accounts for the main list (default 3)
  • Lookback period
  • Sources to read
  • Recipients at product

What keeps you in control

It always asks you first

  • Sending the list to product
  • Promising a feature date to any customer

Hard limits

  • Never adds items to the product backlog directly
  • Never tells customers a feature is planned

It stops when

  • Done: list approved and delivered
  • Stop: no notes logged in the period

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensFrom 180 deal notes in March, the agent found 47 requests. 31 matched existing items, but 16 did not, so the match check failed for those. It grouped them into 4 themes, and a manager confirmed 3. The top request, single sign-on for a second identity provider, was tied to $1.2 million in pipeline across 9 accounts. The VP approved the list.

More agents for product managers