Attending Innovate QA? Get George's free QE Interview Prep Kit.
Get the KitThings I have built. Quality engineering tools, experiments, and contributions to open source.
github.com/george-andrawsA tool that generates test cases from product requirements using Claude, GPT-4.1, and Gemini in parallel, then scores each model's output with both human and LLM-as-judge scoring. Tracks quality trends across prompt revisions with Langfuse observability, includes CLI scripts for batch experiments, and ships with 138 tests across 12 suites.
An end-to-end quality engineering study. I built a Coptic hymns web app with AI, then used Claude, GPT-4, and Gemini to generate test cases, write automated Cypress tests, and analyze the results side by side. A practical look at where LLMs genuinely help in test automation and where they still fall short.
My personal site and ongoing build playground, where I prototype new web and AI ideas. Private repository, actively maintained.
A local research package for Coptic Orthodox lectionary study. Generates indexed CSV/JSONL data from source readings across Pascha, Agpeya, and special services, with a query helper for looking up Bible chapters and cross-referencing passage coverage from 2020–2035.
contributed to nesquena/hermes-webui
REPLACE THIS with one sentence describing what you actually contributed (e.g. "Added mobile PWA support and fixed X"). Only keep this entry if you have a merged PR or accepted commits upstream.