AI QA, explained
The AI QA category is young and noisy. These posts define what an AI QA engineer actually is, how the trust architecture works — AI investigation backed by browser evidence — and where the category is heading. The honest answer to "can I trust an LLM to test my site?" lives here.
Start here: Why Prufa exists
-
Agentic testing vs scripted testing: can you trust an LLM?
Agentic tests aren't flaky if plain code does the verifying. The honest hybrid: the LLM navigates, deterministic code grades — how to tell tools apart.
-
Chaos testing for web apps: what it is, and what an LLM adds
What chaos testing for web apps is, how it relates to monkey testing, and what an LLM adds — plus where it fits next to your end-to-end tests.
-
Why Prufa exists: QA built for the agentic era
AI writes 10× more code than humans can validate. The QA gap isn't a missing test suite — it's surface area. Here's the architecture we bet on.