Agentic QADjangoLLM Evaluation
Agentic QA: Evaluating Chatbot Accuracy with AI/ML Pipelines
Building an in-house agentic QA product that automatically tests chatbot responses for accuracy, relevance, and consistency.
Agentic QA is an AI chatbot accuracy and quality analysis tool I built to solve a real problem: how do you know your chatbot is giving reliable answers?
The Django/Python backend runs automated test cases and evaluation pipelines. The React dashboard visualizes performance metrics including accuracy, relevance, and consistency scores.
This project strengthened my work around LLM evaluation, prompt engineering, and building practical AI quality tooling.