Quality engineering × applied AI
I build AI-powered testing systems that find defects faster, cut manual effort, and keep enterprise software reliable at scale.
profile
AI makes testing faster. Human judgment makes it trustworthy. My work lives at that intersection.
I've spent the last decade making enterprise systems reliable — building test automation frameworks, data validation pipelines, and quality processes from scratch. Now I'm focused on what comes next: using AI to fundamentally change how we test software.
Every day, I use AI tools in production work — not as experiments but as core infrastructure. I use Claude Code to generate test suites, build API validations, write documentation, and manage test workflows. I've built GPT-based anomaly detection that catches data quality issues — schema drift, distribution shifts, transformation errors — that traditional rule-based checks miss.
I'm now building toward agentic testing: AI agents that autonomously generate test cases, execute them, analyze results, and triage failures — with human oversight at critical checkpoints. I'm building it in production, not just talking about it.
My background spans insurance, enterprise software, and healthcare data systems: complex, regulated environments where getting quality wrong has real consequences.
ai in practice
Claude Code generates Pytest suites, API validations, and data pipeline checks daily. Not one-off prompting — a structured workflow where AI follows our framework conventions and I review and refine. Coverage now reaches edge cases and boundary conditions we previously skipped for lack of time.
AI-powered validation monitors data pipelines across cloud databases, detecting schema drift, distribution shifts, and transformation anomalies rule-based checks can't catch. Integrated into CI/CD as quality gates — bad data stops before it reaches production or customers.
Autonomous test agents that explore applications, identify testable scenarios, generate and execute test cases, analyze results, and file bugs — with human review checkpoints. The goal: testing that scales with AI while keeping the judgment that makes systems trustworthy.
What took hours now takes minutes. The compounding effect: when test writing is cheap, coverage naturally expands.
The teams that win with AI testing won't be the ones that trust it blindly. They'll be the ones that build the right guardrails around it.
capabilities
track record
Insurance technology company
Enterprise software company
Healthcare technology firm
Technology solutions provider
credentials
field notes
AI won't replace testers. But testers who use AI will replace testers who don't. The skill isn't prompting — it's knowing what to test and why. AI handles the how.
On skillsMost "AI testing tools" are wrappers around GPT with a nice UI. The real value isn't the tool — it's building the workflow that makes AI output trustworthy enough to act on.
On toolingI've seen AI generate 50 test cases in 10 seconds. 40 were useful. 8 were redundant. 2 were dangerously wrong. The future of QA isn't generating tests — it's building the guardrails that catch the 2.
On guardrailsAgentic testing is coming: AI agents that explore, test, and report autonomously. The QA leaders who build these systems today will define the field for the next decade.
On what's nextoutput
fetching latest content…
More on Mediumcontact
or drop a note directly: