{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/014f0d089fde4bd9b6906addb5041c0b\" frameborder=\"0\" width=\"1280\" height=\"960\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":960,"width":1280,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":960,"thumbnail_width":1280,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/014f0d089fde4bd9b6906addb5041c0b-ddb38db99d50d2cf.gif","duration":185.858,"title":"Production-Ready AI Agents and RAG Systems","description":"This Loom introduces Ankit’s background and focus on designing and building production-ready AI platform and agent workflows. He highlights expertise in LLM applications, RAG systems, AI agents, prompt engineering, tool calling, and AI platform development, including production pipelines with Python, FastAPI, LangChain, and LlamaIndex. He also mentions experience with OpenAI-based solutions, AWS Bedrock, Azure OpenAI, vector databases, Docker, Kubernetes, and REST APIs, including retrieval and response generation architectures for document ingestion, chunking, embeddings, and vector search. A key theme is taking AI prototypes and making them reliable through scalability, latency, observability, security, evaluation, and cost optimization across the engineering stack."}