This paper presents the K11tech Agentic AI QA System, a LangGraph-orchestrated multi-agent framework that autonomously executes a complete CI/CD quality gate — from pull request analysis to defect filing — without requiring manual QA intervention for routine changes. The system orchestrates 14 specialist AI agents across four pipeline phases, decouples agent logic from external tools via 7 Model Context Protocol (MCP) servers, and incorporates a risk-proportionate Human-in-the-Loop (HITL) gate that suspends execution and requests human review when risk score ≥ 0.85. A self-evaluation layer using DeepEval and RAGAS continuously audits the quality of LLM-generated pipeline outputs. Key results on 120 pull requests across three repositories: 87% reduction in pipeline execution time vs sequential baseline (8.3 min vs 63.4 min) 91.2% defect detection rate (F1 = 0.913) Zero production escapes during the evaluation period Full agent portability confirmed across service substitutions via MCP decoupling Source code: https://github.com/K11-Software-Solutions/k11techlab-agentic-ai-qa-system
Kavita Jadhav (Mon,) studied this question.