Hire an AI product feedback roadmap reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• Each request with a yes, later or no, how many different people asked and one reason
• A proposed roadmap change, each line with its reason
• Short reply drafts with no promised date
• The numbers and requests to watch next week

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Counting one loud person three times.
• Ruling yes because a request is easy to build.
• Adding a feature for new users who are leaving before they reach it.
• Changing many roadmap lines in one week. Say which changes can wait.
• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.

What a good result looks like

An example, not your task: Feedback, support notes and requests pile up and you want the same fair sort every week.

• This week. One line with new items, repeats and how many rulings changed.
• Path taken. Whether it only screened requests or looked into lost new users first, and why.
• Rulings. Each request with yes, later or no, how many different people asked and one reason.
• Roadmap change to approve. Each add, move or cut, with its reason and the step that proposed it.
• Reply drafts. A short reply for each request that earned one, with no promised date.
• Watch next week. One to three requests or numbers that decide next week's path.

How the work is checked

• Each count is of different people, not messages.
• Every yes has its full cost and a place on the roadmap, or on the later list.
• Nothing from numbers.md or decisions.md was used without checking it against this week.
• If new users fell sharply, the first-visit fix comes before any new feature.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Jason Fried and Andrew Chen would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Load the memory. Reads the tally, your product aim, last week's numbers and every earlier ruling from the feedback folder.
• Update the tally. Adds new items, merges repeats and counts different people, not messages.
• Screen the requests. Starts every item at not now, adds up the cost of each yes and rules yes, later or no. Earlier rulings stand unless there are new askers.
• Choose the path. If new-user numbers fell sharply or new users say they are lost, it looks into that first and puts the fix ahead of new features.
• Fit the yes list. If there are more yeses than one cycle can hold, it scores and ranks them and moves the rest to later.
• Hand back one change. Writes a proposed roadmap with each change marked, plus reply drafts, and stops for your yes.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id weekly-product-feedback-triager only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/weekly-product-feedback-triager/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• This week's feedback, with who said it and the date
• Your current roadmap and how much room the next cycle has
• What the product is for and who it is not for, the first time
• This week's product numbers, such as visits, sign-ups and 30-day users (optional)

Helpful context (optional)

• Your last three months of requests, to start the tally
• The commitments already made to customers

Tools and access

• Claude Code: It can keep the feedback folder, read earlier weeks and run on a schedule.
• Your support inbox or feedback tool: Export the week's messages with names and dates so repeats are counted fairly.
• Any good chat AI: Counting, costing and drafting short replies is text work.
• Your support inbox or feedback tool: Real request counts come from there.
• Any good chat AI: Funnel shares and plain-language findings are text and arithmetic work.
• Your analytics tool: Gives the exact counts the skill needs, by period.
• Claude or ChatGPT: Either can write the updates. Neither can read your git history, so paste the commits or run the script yourself.
• Git and Python 3: Needed only if you want the changelog script to read your git history.

Functions and deliverables

• Product feedback roadmap reviewer: Group product requests by distinct people. Get supported yes, later or no proposals and a roadmap change to review.
  • Each request with a yes, later or no, how many different people asked and one reason
  • A proposed roadmap change, each line with its reason
  • Short reply drafts with no promised date
  • The numbers and requests to watch next week
• Feature request screener: Screen your feature requests and get a yes, later or no on each, with the full cost of every yes and a kind reply for the customer.
  • A repeat count per request, from different people, over time
  • The hidden costs of each request that repeats
  • A yes, later or no with one reason, and the vision conflict named
  • A short reply for each customer that promises no date
• New user drop-off finder: Find where new users drop off between visit, sign-up and day 30. Get the biggest leak, the missing first-visit step and one fix to measure.
  • Your funnel, with the count and share at each step
  • The biggest drop, ranked, written before any feature idea
  • An estimate of how many sign-ups the feature would reach
  • The step or message missing from the first visit
  • One change for new users, with a measure, a target and a date
• Product metrics review writer: Turn your product numbers into a metrics review: a scorecard against targets, what moved, likely causes and next steps. Paste your figures to start.
  • A scorecard against targets
  • Trends and notable changes
  • Likely causes for spikes and drops
  • Recommended actions
  Source: Anthropic.
• Feature priority scorer: Share your feature list. Get each scored with RICE and ranked, plus interview analysis and a requirements template.
  • Features ranked by RICE score, with an optional JSON or CSV export
  • A shortlist that fits your capacity
  • Pain points and quotes from interviews
  • A requirements template
  Source: Alireza Rezvani.
• Roadmap update writer: Turn your product plans into a roadmap update for executives, engineers or customers. Get the roadmap story, release notes or a changelog, one per reader.
  • A roadmap in the format that fits how certain your plans are
  • One update for each reader you named
  • Customer-facing or internal release notes
  • A changelog grouped by type of change
  • A list of details you still need to supply
  Source: Alireza Rezvani.
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• Jason Fried: Cut a project to a focused first version through Jason Fried’s recorded approach. Keep the core useful, reduce scope and protect a calmer workweek.
  • Your problem worked on the way Jason Fried would: their questions, their method, their push-back
  • The answer or the work, in Jason Fried's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Andrew Chen: Review product growth, returning users or a two-sided market using Andrew Chen’s public work. Start with the funnel and the smallest useful network.
  • Your problem worked on the way Andrew Chen would: their questions, their method, their push-back
  • The answer or the work, in Andrew Chen's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Feedback, support notes and requests pile up and you want the same fair sort every week.
• The same request keeps coming back and you want to know how many different people asked.
• Sign-ups look fine but fewer new people stay, and you want that checked before you build more.
• A big customer asks for a feature and you need a fair, written reason to say yes, later or no.

Limits to check before starting

• You have one feature decision to make. Use the Feature request screener on its own.
• You have no written product aim and don't want to write one. Every ruling depends on it.
• You only want to know why new users leave. Use the New user drop-off finder.
• You need a polished roadmap story for your team or customers. Use the Roadmap update writer after you approve the change.
• You get a handful of messages a month. A weekly tally adds more work than it saves.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to triage this week's feedback.
• Put the week's feedback and your roadmap in one folder, or attach them in the chat.
• The first time, give it your product aim. It saves that and keeps the tally in a feedback folder. In a plain chat with no files, paste the tally it gave you last week.
• Starting from nothing? Paste your last few months of feedback to seed the tally. If you have none, it starts a new tally this week.
• Read the rulings and the roadmap change. Say yes to the lines you agree with, and send the replies yourself or ask it to prepare them.
• Run it again next Monday. It adds to the same tally.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/weekly-product-feedback-triager for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.