Sold by: Mphasis
Deployed on AWS
Automate persona based UX testing on live web interfaces using AI agents. Captures evidence, measures metrics, and generates comparative accessibility reports.
Overview
Persona Runner is a persona-driven UX testing and reporting platform that orchestrates AI browser agents to simulate real user personas on any live web interface. Built for accessibility conscious development teams and QA engineers, it evaluates websites through the lens of an Elderly User (limited dexterity, large fonts preference), a Color-Blind User (contrast sensitivity), a University Student (speed-focused, multi-tab), and a Cognitive/Dyslexic User (plain language, clear navigation). Each persona is configured with defined abilities, frustrations, interaction patterns, and success goals delivering qualitative and quantitative UX insights that traditional automated tests cannot provide.
Key Features and Benefits:
- AI-powered persona simulation using browser-use and OpenAI, executing realistic multi-step journeys on live production or staging websites with zero code changes required on the target site
- Automated evidence capture: screenshots at each interaction step, raw interaction logs, and structured per-persona UX metric scores
- AI-generated findings reports served through a clean React + Tailwind SPA dashboard, with severity-ranked issues and actionable recommendations
- Side-by-side comparative run analysis across multiple personas or successive deployments, enabling UX regression detection in CI/CD workflows
- Server-Sent Events (SSE) streaming for live run output and a full REST API for programmatic integration with existing toolchains
Highlights
- AI persona simulation drives real browser sessions as Elderly, Color-Blind, Student, and Dyslexic users, surfacing accessibility barriers and UX friction on any live website, without modifying the target site.
- Automated evidence capture and AI-generated reports: each persona run records screenshots, interaction logs, and accessibility metrics, delivered as severity-ranked findings in a clean React dashboard.
- Side-by-side comparative analysis across multiple UX test runs lets teams spot persona-specific regressions and cross-run accessibility gaps, with REST API and live SSE streaming for CI/CD integration.
Details
Sold by
Categories
Delivery method
Supported services
Delivery option
Browser-Use UX Testing Platform CloudFormation
Latest version
Operating system
Linux
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/unit |
|---|---|---|
Inference | Users are charged per request | $0.50 |
Vendor refund policy
We currently do not have a refund policy. For further details regarding production and costs, please get in touch with the Mphasis NEXT Labs team on the below provided URL : https://www2.mphasis.com/AWS-Marketplace-Support-LP.html
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Browser-Use UX Testing Platform CloudFormation
Supported services: Learn more
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Browser-Use UX Testing Platform
Additional details
Usage instructions
Persona-Driven Browser-Use UX Testing Platform
AWS Marketplace Buyer Instructions
Description
Deploys the Persona-Driven Browser-Use UX Testing Platform as an Amazon ECS Fargate service behind an ALB. The platform launches AI browser agents simulating personas (Elderly, Color-Blind, Student, Dyslexic) against any web interface. Agents navigate, capture evidence, and generate UX reports with accessibility scores. A PostgreSQL RDS instance stores test data and metering.
Supported services: Amazon ECS Fargate, RDS (PostgreSQL), AWS Bedrock, Marketplace Metering.
Usage Instructions
Complete ALL prerequisites before launching. Estimated prep time: 20 to 40 minutes.
Full details in the deployment guide: Persona_Runner_Customer_Deployment_Guide.pdf
Summarized Instructions
Before Launching
-
Network
- VPC with DNS enabled
- 2 public subnets (ALB/ECS) and 2 private subnets (RDS) in different AZs
-
Security Groups
- Create one App SG: inbound TCP 8000 from user CIDRs; all outbound allowed
- Used by both ALB and ECS
-
IAM Roles
- ECS Task Execution Role: AmazonECSTaskExecutionRolePolicy + Secrets Manager read
- ECS Task Role: bedrock:InvokeModel on * and bedrock-agentcore:*
- Recommended regions: us-east-1 or us-west-2
-
Secrets Manager - create a JSON secret with these keys:
Key Value PGHOST / DB_HOST Leave blank; update post-launch with RDS endpoint PGPASSWORD / DB_PASSWORD Matches DbPassword parameter PGDATABASE / DB_NAME uiux or preferred PGUSER / DB_USER uiux_user or preferred -
Bedrock Access
- Enable us.anthropic.claude-sonnet-4-20250514-v1:0 in Bedrock > Model Access
-
ACM Certificate (Optional)
- For HTTPS, note the ARN
- Leave blank for HTTP (port 80)
Launching the Stack
Subscribe on Marketplace, then Launch CloudFormation with these parameters:
| Parameter | Description |
|---|---|
| VpcId | Existing VPC ID |
| PublicSubnetA / PublicSubnetB | Public subnets |
| PrivateSubnetA / PrivateSubnetB | Private subnets |
| ExistingSecurityGroupId | App SG ID |
| ExecutionRoleArn | Task Execution Role ARN |
| TaskRoleArn | Task Role ARN |
| DbPassword | RDS password |
| RuntimeSecretArn | Secret ARN |
| CertificateArn | ACM ARN (optional) |
Wait for CREATE_COMPLETE (10 to 15 mins). Note ALBDNSName and RdsEndpoint from the stack Outputs.
Post-Deployment
-
Update Secrets - update PGHOST and DB_HOST in Secrets Manager with the RdsEndpoint.
-
Restart ECS:
aws ecs update-service --cluster <ProjectName>-prod-cluster --service <ProjectName>-prod-backend-api --force-new-deployment -
Verify - open http://<ALBDNSName>. Go to New Run, enter a URL, select a persona, and click Start Run.
-
Results - view logs, scores, and PDF reports under Runs.
Support
Vendor support
For technical support, deployment assistance, or general enquiries, please contact the NEXT Labs team at Mphasis. Website:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Identify and align with your most critical personas—the individuals and roles that both drive business outcomes and represent the highest risk. By understanding who matters most, Loom Security helps organizations tailor their security posture for maximum impact and reduced exposure. This persona-centric approach ensures your cybersecurity strategy aligns with business priorities, not just technical checkboxes.
By BMRLab
atypica AI is an AI powered business research platform that helps teams understand how people think decide and react in real market situations. It uses multiple AI agents that work together to explore consumer emotions opinions and decision drivers instead of relying only on numbers and surveys.
With built in research planning social listening interview simulation and persona modeling atypica AI helps product marketing and strategy teams quickly turn questions into clear insights. The system remembers past studies and continuously improves its understanding so teams can avoid repetitive research and focus on better decisions faster.
Advanced behavioral simulation built on real data from your audience. Stable personas that think, respond, and decide with their own logic to validate hypotheses in days, without guesswork.
Human-validated synthetic personas that align, tune, and evaluate your AI models with research-grade accuracy. Limbik provides persona-labeled training examples, fine-tuning services, and resonance evaluations to ensure your models generate outputs trusted by the audiences they serve. Built for Amazon Bedrock, SageMaker, and custom LLM pipelines.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.