Agent or script? A decision framework for AI in test automation
Most QA teams reach for an agent when a script would be cheaper and more reliable. A practical framework for deciding which one a task actually needs.
Read the articleInsights
Insights on AI-native quality engineering
Notes from building AI systems inside real delivery pipelines — what works, what quietly fails, and what interviewers actually ask about it.
Self-healing test automation quietly hides real defects. Here is how to stop it.
Self-healing keeps suites green, which is the problem. A three-layer design, plus the heal history and review loop that stops it masking regressions.
Read the articleAI test generation without hallucinated steps: a grounding checklist
Why LLM-generated test cases invent steps that do not exist, and the retrieval, structuring and evaluation controls that stop it happening at production scale.
Read the articleNext cohort
The practice behind the writing.
Everything here is taught in the 100-day program, with a mentor and reviewed project work.
Cohort snapshot35 seats
01100 days live + self-paced15 wks
02Mentor-led weekend classes10 hrs/wk
038 guided projects + capstoneportfolio
04Interview prep & career supportongoing
Weeknight office hours · lifetime access to recordings · one accountable mentor across all 100 days