Manoranjan Rajguru

Manoranjan Rajguru

AI Architect

About

Manoranjan Rajguru is a seasoned AI and Generative AI leader currently working with Microsoft with over 14 years of experience in Software Development, Data Science, and Machine Learning. He currently serves as Lead Engineer – Generative AI at Allstate, where he architects enterprise-scale GenAI systems leveraging LLMs, RAG, and agentic frameworks. With deep expertise across Azure OpenAI, LangChain, NLP, OCR, MLOps, AWS, and Azure, Manoranjan specializes in building production-ready AI solutions that drive measurable business impact.

 

The era of agentic AI has arrived, and open-source tooling is leading the charge. Developers are now building autonomous, multi-agent workflows faster than ever before. These systems go beyond traditional chatbots, taking on complex tasks that would otherwise require hours of manual effort.

At the heart of this framework lies the Agent Harness, the execution layer that provides agents with controlled access to the shell, file system, and messaging loops. In this session, we'll explore how Agent Harness serves as the backbone of reliable, enterprise-safe agent execution, covering key capabilities such as session isolation, skill registries, and MCP Toolbox integration.

Whether you're building your first agentic application or scaling AI automation across an enterprise, this session will provide practical insights into designing, deploying, and managing agents effectively.

Read More →

This full-day, hands-on workshop is for those who want to go beyond basic chat applications and learn how to build, extend, orchestrate, and deploy enterprise-ready AI agents on Azure. Participants will work with Azure AI Foundry, Foundry Agent Service, Foundry IQ, and the Microsoft Agent Framework to create agents, integrate built-in and external tools such as File Search, Code Interpreter, Bing Grounding, custom functions, and MCP servers, and design multi-agent workflows using visual orchestration, code-first patterns, connected agents, and A2A. Across four hands-on labs, learners will build working agents, connect tools and knowledge sources, explore when to use Foundry Agent Service versus Microsoft Agent Framework, and apply production best practices for monitoring, security, deployment, governance, scaling, and cost management. By the end, they will have a practical understanding of how to choose the right Azure-based agent architecture and build real-world agent systems confidently.

Read More →