Quality leadership,
at enterprise scale.
Twenty-two years directing quality engineering strategy across fintech, banking, and enterprise — building high-performing teams, AI-augmented delivery pipelines, and the culture that lets organisations ship with confidence.
What I'm doing now
AI-Powered Testing
Multi-agent systems for test automation using Playwright, MCP, and LLMs. Practical reliability over self-healing buzzwords.
LLM Evaluation Pipelines
Evaluation pipelines for RAG systems using DeepEval. Prompt regression testing integrated directly into CI/CD.
Release & Reliability
Release management, incident response, observability, and DORA metrics wired into how teams actually work.
Engineering Coaching
ICAgile-certified coaching (ICP-ACC, ICP-ATF) and 1:1 mentorship for engineers, leads, and managers.
Skills & stack
playwright-spec-doc-reporter
Playwright reporter with BDD annotations, AI failure analysis, and interactive HTML dashboards.
Multi-Agent QA Framework
Four specialised agents with DOM Memory architecture for persistent selector knowledge.
DeepEval Production Pipelines
LLM evaluation for RAG systems — faithfulness, relevancy, and hallucination detection in Azure DevOps.
AI Safety & Validation Engineering for Financial AI
Evaluators, adversarial suites, explainability, telemetry, and circuit breakers — a field guide to safety as an engineering discipline.
Building Engineering at Scale: The 0-1-n Quality Problem
Most teams crack 0-to-1. Few survive 1-to-n. Two decades of lessons on building quality at scale.
From TDD to Spec-Driven Development
TDD gave us confidence. BDD gave us collaboration. Spec-driven development gives us a single executable source of truth.
Background
Trading systems, blockchain, financial services, real-estate tech — two decades directing how high-stakes organisations think about quality.
Let's talk.
Mentorship, coaching, speaking, or a straight conversation about quality at scale — reach me on any of these.