Agentic AI, LLM engineering, and the models behind modern automation — multi-agent systems, LLM evaluation and comparisons, RAG, fine-tuning, AI infrastructure, security, and production AI engineering.
From the blog
A curated guide to the best newsletters, conferences, communities, research papers, and experimentation habits for keeping your agentic AI skills sharp as the field evolves rapidly.
Apply the strangler fig pattern to incrementally migrate a monolithic AI agent to microservices. Learn routing cutover strategies, feature parity validation, and safe rollback techniques.
Implement the Strategy pattern to dynamically swap AI agent behaviors at runtime — supporting A/B testing, context-driven model selection, and flexible agent configuration.
Implement real-time token-by-token streaming from AI agents using FastAPI's StreamingResponse and Server-Sent Events. Covers async generators, error handling during streams, and JavaScript client integration.
Build real-time streaming AI pipelines using Python async generators. Learn yield patterns, consumer chains, and backpressure for delivering LLM tokens to users instantly.
Learn how to stream OpenAI responses token-by-token using the Python SDK, implement async streaming for web applications, and display incremental results to users.
Learn how to stream structured outputs from LLMs for real-time UI updates. Covers partial JSON parsing, streaming with Instructor and Pydantic, progressive UI rendering, and handling incomplete data.
Implement token-by-token streaming display for AI agent responses using Server-Sent Events, React state, and cursor animation. Includes markdown rendering during streaming.
Build an AI agent that processes Stripe webhook events for payments, subscriptions, and invoices with proper handler routing, state management, and failure recovery.
