The work

Built with curiosity.
Made to be useful.

AI experiments, reliable automation, and products that connect the dots. Explore the projects and the thinking behind each one.

All repositories

7 projects to explore

AI & agents

SideBySide

A local workbench for finding the right model, gateway, and agent setup for the job.

  • Next.js
  • TypeScript
  • Docker
  • MCP
Behind the build
The problem
Comparing AI gateways means juggling configurations, responses, costs, and decisions across disconnected tools.
The approach
Built a shared playground for model comparisons, benchmarks, MCP exploration, and Docker-based coding-agent sandboxes.
What it enables
Prompts, run history, and model decisions stay together in a local workspace, with agent experiments isolated from everyday CLI settings.
Read the repository

AI & agents

QA Agent

From a user story to browser validation, with explicit checks behind every result.

  • TypeScript
  • Playwright
  • Cypress
  • LLM tooling
Behind the build
The problem
AI-generated test steps need execution control and verification before their results can be useful.
The approach
Separated agent reasoning, deterministic orchestration, and verification into a modular TypeScript harness, with recovery and code generation.
What it enables
The harness produces execution reports and generated Playwright or Cypress tests. LLM generation is optional, with built-in templates as a fallback.
Read the repository

AI & agents

QA Master Agent

Application knowledge, workflow memory, and browser execution in one QA platform.

  • React
  • Node.js
  • Playwright
  • RAG
Behind the build
The problem
An agent needs context about an application’s behavior and workflows to carry out meaningful QA work.
The approach
Combined knowledge ingestion, graph-based memory, retrieval, provider routing, and Playwright execution with an operational UI.
What it enables
The project connects persistent application knowledge to browser sessions, execution history, and captured evidence.
Read the repository

Products & platforms

ReportArch API

A home for automated test reports, organized around the teams and projects that need them.

  • Express
  • MongoDB
  • AWS S3
  • DynamoDB
Behind the build
The problem
Test reports need to be stored, organized, and retrieved beyond an individual test run.
The approach
Built an Express API covering organizations, projects, suites, report uploads, users, authentication, and API keys.
What it enables
A backend for archiving and viewing reports, using MongoDB alongside AWS storage services.
Read the repository

Quality engineering

SwagLabs BDD

Readable acceptance tests backed by Playwright browser automation.

  • Cucumber
  • Playwright
  • JavaScript
  • BDD
Behind the build
The problem
Behavior-driven specifications need a practical connection to browser execution.
The approach
Combined Cucumber and Playwright for acceptance testing on the SauceDemo storefront.
What it enables
A reference project for expressing browser tests as behavior-driven scenarios.
Read the repository

Products & platforms

LinkDrive

A dedicated place to organize links and keep useful resources within reach.

  • Next.js
  • JavaScript
  • Product development
Behind the build
The problem
Useful links become difficult to find when they’re scattered across tabs and messages.
The approach
Built a link organization application with a web interface and backing storage.
What it enables
A product exploration around organizing and managing collections of links in one place.
Read the repository

Products & platforms

Infrastructure in Code

Provision a static website on AWS S3 through version-controlled infrastructure.

  • Terraform
  • AWS
  • S3
  • IaC
Behind the build
The problem
Manual cloud setup makes deployments harder to reproduce.
The approach
Defined an S3 static website deployment with Terraform infrastructure as code.
What it enables
A source-controlled reference for provisioning and deploying a static website on AWS.
Read the repository

Have something in mind?

Let’s bring it to life
and create lasting value.

An idea to explore, a problem to solve, or something you believe could be better. I’d like to hear about it.