K.Tanvik Reddy

A complete guide to building enterprise-grade AI agents using Google Cloud — covering GKE, Cloud Run, Vertex AI, Model Armor, MCP, and agent communication protocols

My study on Agentic AI architectures and workflow patterns used in real-world systems like research agents, coding agents, and orchestration frameworks.

My notes and learnings while implementing MCP OAuth authentication, JWT verification, authorization, and protected MCP servers.

An MCP-powered agentic RAG assistant built with FastMCP, Qdrant, BGE-small embeddings, RAG reranking, Gemini generation, evidence verification, and Bright Data web fallback.

Hands-on experiments with OpenAI Playground covering prompt design, model comparison, tool/function calling, structured outputs, and eval-driven prompt improvement.