01Under construction
LLM testing
Functional behaviour, robustness, safety, consistency, and model-change regression.
Generative AI & LLM testing
02Under construction
Evaluations
Datasets, rubrics, model graders, human review, thresholds, and experiment tracking.
03Under construction
RAG
Retrieval quality, grounding, citations, chunking, permissions, and freshness.
04Under construction
Prompt security
Prompt injection, data leakage, tool misuse, and layered mitigations.
05Under construction
Observability
Traces, token usage, latency, failures, feedback, and production diagnostics.
06Under construction
Pet projects
Practical QA copilots, test generators, review tools, and evaluation harnesses.