Built QLANKR Test to make AI evaluation less vibe-based

I built QLANKR Test because testing AI systems still feels too inconsistent and too dependent on guesswork.

Lots of people are building agents, chatbots, RAG systems, and tool-calling workflows, but the feedback loop is often messy. You run something, tweak a prompt, change a tool, and try again, but it is not always easy to understand what actually improved.

QLANKR Test is my attempt to make that process more structured.

The product lets you test AI agents, chatbots, RAG systems, and tool-calling workflows, then review a report and get a QI score in minutes.

What I care about most right now is:
- whether the report feels genuinely useful
- whether the score makes sense
- what is still missing for real-world AI testing

If anyone here works on AI products, agents, or evaluation workflows, I would really love honest feedback.

Site: https://test.qlankr.com