AI-Driven Quality Engineering Architect · Available for new engagements · Australia

SNK
SNK Digital
Back to Services

AI-Augmented Testing

AI test generation · self-healing · intelligent automation

LLM-assisted test pipelines that accelerate authoring, reduce flaky test maintenance, and surface richer failure context. I design and ship AI stages that integrate with your existing framework rather than replacing it — from AC clarification through to LLM-driven failure triage and Tier 4 self-healing locator re-binding.

Best suited for

LLM test gen pipelinesSelf-healing locator strategyLLM-as-Judge for output grading
Discuss this serviceBook a 15-min call

What's included

  • LLM test generation pipelines grounded in framework conventions
  • AC clarification stage (LLM-driven, audit-traceable)
  • Tier 4 self-healing locator re-binding
  • LLM-driven failure triage and root-cause classification
  • LLM-as-Judge for log validation and output grading
  • Promptfoo and DeepEval evaluation harnesses
  • RAG pipeline evaluation (RAGAS, LangChain)

Related work

Evidence and reference architectures

Client engagements are anonymised under NDA — references available at screen stage. Reference patterns are illustrative architectures for this problem class.

EnergySep 2025 – current

AI-Augmented Playwright Test Pipeline for a Large Australian Energy Company

I was engaged as Senior Test Automation Lead at a large Australian energy retailer with national customer-facing digital surfaces and back-office systems. The business ran customer portals, loyalty and payment flows…

PlaywrightTypeScriptAI-driven test genPromptfooLLM-as-Judge
Read case
Open R&DApril 2026 – ongoing

AgentQE Continuum — Event-Driven, Self-Healing QA Validation System

An open R&D system that takes a CI test failure event end-to-end through ingestion, LLM-based root-cause analysis, confidence-scored decisions, and (where safe) autonomous fix generation. The patterns I now apply to client engagements were proven here first.

LangGraphClaude APITypeScriptPostgreSQLpgvector
Read case

Reference patterns

Agentic QE

Agentic / Self-Healing Test Framework (Tier 4 LLM-Assisted Re-Binding)

Playwright · LLM · Claude API · Promptfoo · LLM-as-Judge

Ready to improve your software quality?

Book a consultation and let's discuss how I can help your team build, test, and scale with confidence.