The Death of the Flaky Test: Why I Stopped Writing Scripts and Started Architecting Agents
Ivan Dimov
Command Palette
Search for a command to run...
Archive
18 posts published so far
The RAG Triad in 2026: Testing with LLM & DeepEval
Ivan Dimov
The $47k Loop: Why Your AI Agent Needs a Circuit Breaker
Ivan Dimov
Why Your RAG App Is Slow (and how to prove it)
Ivan Dimov
The Evaluation Bottleneck: Building a "Golden Dataset" Without Losing Your Mind
Ivan Dimov
Stop Counting Words: The "Token" Mindset in LLM Engineering
Ivan Dimov
QA’s New Frontier - Trust as a Quality Metric
Ivan Dimov
Contain the Damage
Ivan Dimov
The Automated Confidentiality Tripwire
Ivan Dimov
Inside the LLM Leak
Ivan Dimov
Adversarial Prompt Testing
Ivan Dimov
When Models Talk Too Much
Ivan Dimov
The Invisible Hand
Ivan Dimov
From Lab to Live
Ivan Dimov
LLMs in the Testing Trenches
Ivan Dimov
The Evaluator's Toolkit
Ivan Dimov
Building Your LLM Testing Suite
Ivan Dimov
The LLM Testing Paradigm Shift
Ivan Dimov