Prashanth Kunreddy

About

Built production LLM/agent systems for procurement and contract spend controls, including a proactive contract value leakage detection platform that moved an organization from reactive audits to pre-payment rejection. Combines multi-agent orchestration (Semantic Kernel/LangChain/AutoGen), document AI benchmarking (Textract vs Azure DI), and MLOps/testing (MLflow, QTest/Pytest) with strong security practices (RAG-grounded responses to prevent prompt injection). Integrated anomaly alerts directly into SAP SES workflows and Power BI dashboards, citing ~$38M leakage addressed across large spend environments.

Experience

Education

Key Strengths

• Built and deployed proactive contract value leakage detection system shifting org from reactive audits to pre-payment rejection
• Achieved 99.9% extraction accuracy via self-correcting GPT pipeline and Chain-of-Thought prompting
• Strong document AI benchmarking; selected AWS Textract over Azure DI (reported 6.36x better performance for tables)
• Designed multi-agent orchestration with supervisor agent/tool use (Semantic Kernel) for complex rule execution
• Integrated AI anomaly alerts into SAP SES approval workflow to drive operational adoption
• Implemented LLM security controls by grounding responses in RAG to mitigate prompt injection
• Established testing/evaluation approach using MLOps lifecycle (MLflow), confidence scores, and validation with QTest/Pytest
• Delivered measurable business impact: addressed ~$38M leakage; referenced $250M spend scope and $30B annual spend context