Use browser automation to experience a product through several evidence-based personas and compare where their journeys diverge.
12:26 to 18:31: Claire asks the browser agent to use the same product as several distinct personas and compare the resulting journeys and critiques.
A comparative research report grounded in observed product behavior for each persona.
OpenAI conversational AI
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
Define 2-3 distinct user personas with specific goals for using your product. For example, you could model a hurried PM, a detail-oriented engineer, and a team leader, each with a different task to complete.
Define each persona by job, context, goals, constraints, current behavior, and source evidence.
Craft a multi-part prompt that instructs the AI to adopt each persona in sequence. For each one, define the task they need to perform and ask the AI to provide a qualitative critique of the experience. A dictation tool like Monologue can be useful for creating complex prompts.
Use [product URL] as each persona and complete [journey]. Record actions, hesitation points, missing information, and outcome.
Open your product in the AI desktop app's browser. Paste your multi-part prompt to begin the test. The AI will take control of the browser to navigate your product as each persona.
Run the same journey independently for all personas without carrying conclusions between sessions.
The AI will generate a document with its research critique. Review its findings, paying close attention to any 'structural breaks' or friction points it discovered while attempting to complete tasks from each persona's perspective.
Compare the evidence by persona, then identify shared friction, divergent needs, and the product changes best supported by observation.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building
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.
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.
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.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.