←Back/Product/Claude
IntermediateProduct

Build a Multi-Persona 'Sub-Advisory Board' for Instant Feedback

Create a powerful review agent in Claude Cowork that simulates a roundtable of advisors with different personas to pressure-test your work and get multi-faceted feedback instantly.

Build a Multi-Persona 'Sub-Advisory Board' for Instant Feedback

Source episode · 27:18

How I AI: JJ Englert's Guide to a 'Daily Operating System' with Claude Cowork

with Claire Vo

27:18 to 34:03: JJ creates a Cowork skill with several named advisor personas, then asks the group to challenge a live decision from different viewpoints.

Read the full episodeWatch on YouTubeListen on SpotifyListen on Apple

Before you start

What you need

  • A decision, draft, or plan with enough context to evaluate
  • Three to five advisor personas with expertise, incentives, and blind spots
  • The criteria and constraints that matter to the final choice

What you’ll make

A structured advisory response with distinct persona views, points of disagreement, shared risks, and a practical recommendation.

Tools used

Step by step

The workflow

Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.

3 steps

Step01

Define the Multi-Persona Review Agent

Define the set of reviewers you want the AI to simulate. These 'sub-agents' will act as your advisory board. For the work you want reviewed, choose personas that represent relevant perspectives, such as different ideal customer profiles, an engineering lead, or your direct manager.

Example prompt
Help me define 3-5 personas to act as a sub-advisory board for reviewing my [type of document, e.g., marketing copy, product spec]. The personas should represent [key stakeholders, e.g., my target customer, an engineering lead, my boss]. For each persona, define their role, primary concerns, and what they look for in a successful document.
Step02

Prompt the Skill Creation

In Claude Cowork, prompt the creation of a 'review agent' skill. Specify that this skill must launch a series of sub-agents, each representing one of the personas you just defined. This instruction tells the tool how to structure the feedback.

Example prompt
I want you to build another uh, skill, and this is gonna be a review agent. For this skill, you're gonna launch a series of subagents that have each their own persona. And this can differ per the task, but an example is if we're launching a newsletter, we want to have subagents that represent our ICP. Maybe for me it would be AI builders, AI executives, and AI interested people.
Step03

Apply the Skill to Your Work

With the skill saved, apply it to a document like a product requirements document or a marketing email. Cowork will generate a multi-faceted critique from the perspective of each defined persona, helping you pressure-test the work and find blind spots before sharing it.

Example prompt
With the skill saved, apply it to a document like a product requirements document or a marketing email. Cowork will generate a multi-faceted critique from the perspective of each defined persona, helping you pressure-test the work and find blind spots before sharing it.

My actual values:
[insert the files, settings, accounts, or constraints for this step]

Give me the exact commands, settings, or output to use. Finish with a pass or fail check for apply the skill to your work.

What good looks like

  • Each persona applies a genuinely different lens
  • The response surfaces disagreement instead of forcing consensus
  • The recommendation cites the strongest evidence and unresolved risk

Build your next product with ChatPRD

Turn an idea into a PRD, user stories, and a plan.

Try ChatPRD free

After the steps

Runbook notes

How to recover when the loop fails and where human judgment helps.

Recover

If it goes sideways

All personas repeat the same generic advice
Give each advisor a concrete role, incentives, expertise, and a question only that persona should answer.
The board produces debate but no usable decision
Require a final synthesis with options, tradeoffs, recommendation, and the next test that would reduce uncertainty.

Keep building

Related workflows

Create an Automated Workout Tracker with a Simple Claude Voice Note
beginnerPersonalClaude

Create an Automated Workout Tracker with a Simple Claude Voice Note

Log your workouts effortlessly without ever opening a spreadsheet. This workflow uses the Claude mobile app to parse a simple voice note and automatically update your workout tracking spreadsheet in the background.

Open
How to Rebuild Your Gmail Inbox Inside Claude to Manage Email
advancedOperationsClaude

How to Rebuild Your Gmail Inbox Inside Claude to Manage Email

Create a custom email management interface within Claude to read, triage, and draft replies without opening the Gmail tab. This workflow helps you reclaim focus and compound your learnings by training your AI on every interaction.

Open
Automate Client Proposals and Onboarding with a Claude 'Pipeline Operator'
intermediateSalesClaude

Automate Client Proposals and Onboarding with a Claude 'Pipeline Operator'

Build a fully automated system in Claude to generate personalized, interactive HTML proposals and client onboarding materials, saving hours on administrative work and creating a high-touch experience.

Open

Start shipping
better products.

Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.

Start building freeRequest a demo
Free to start
No credit card
SOC 2 certified
Enterprise ready