MyTechExp

  A claims processing system with three services that communicate using Google's A2A (Agent-to-Agent) protocol over JSON-RPC 2.0 : 🔹 A Gateway that handles auth, guardrails, and routing 🔹 A Claims Agent that validates claims and checks for fraud 🔹 A Policy Agent that answers coverage and benefits questions Each agent publishes its own capabilities at a standard /.well-known/agent-card.json endpoint — meaning any A2A-compatible client can discover what it does without me hard-coding anything. Same pattern you'd use to plug into a partner agent in real production. 🛠️ The stack ✅ FastAPI + Pydantic for the JSON-RPC layer ✅ LangGraph for stateful agent reasoning (StateGraph + checkpointing) ✅ MCP (Model Context Protocol) for clean tool abstraction ✅ Anthropic Claude — using Haiku for routing, Sonnet for reasoning, Opus reserved for hard cases ✅ LangSmith for end-to-end observability ✅ Custom guardrails for PII detection and prompt injection 🔍 Why this combo clicks M...

  I spent the last few weeks building something I've always wanted — a GenAI app that actually understands cricket. Not just "who's winning" — but why , and what to do about it. Here's what I built: T20 Cricket Score Prediction using a full RAG pipeline. The stack: Google Gemini 2.5 Flash as the LLM brain Pinecone as the vector database for semantic search over match stats sentence-transformers for local embeddings (free, no API cost) CricAPI for live T20 data Streamlit for the web UI + Docker for deployment The interesting part? I gave it this prompt: "Analyze the 2026 T20 World Cup Super 8 standings. Calculate the exact win/loss margins India needs to qualify over West Indies. What happens if Sunday's match gets washed out? And what does Pakistan need against Sri Lanka?" It came back with NRR calculations, rain-rule implications, powerplay strategies for the trailing team — all backed by retrieved data, not hallucination.That's RAG working as ...