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
Build a data analysis chat agent using the OpenAI Agents SDK CodeInterpreterTool that executes Python code, generates visualizations, processes uploaded files, and returns structured results.
Build a streaming chat UI for OpenAI Agents SDK chat agents using run_streamed(), FastAPI SSE endpoints, and a React frontend with real-time token rendering.
Complete developer guide to Anthropic's Claude Agent SDK — installation, agent creation, tools, multi-agent patterns, error handling, and production deployment.
Build a complete multi-agent code review system with specialized agents for analysis, security review, style checking, and a manager agent that synthesizes findings into actionable review comments.
Learn how to build browser automation agents with the OpenAI Agents SDK ComputerTool, implementing the AsyncComputer interface for screenshot capture, mouse clicks, and keyboard input.
Learn production-grade content moderation patterns for AI agents including moderation agent guardrails, rate limiting, abuse prevention, and red-teaming strategies using the OpenAI Agents SDK.
Master conversation branching, undo operations with pop_item, history pruning strategies, and session input callbacks for advanced history customization in the OpenAI Agents SDK.
Build custom session backends for the OpenAI Agents SDK by implementing the SessionABC protocol with complete DynamoDB and MongoDB examples and testing strategies.
Learn how to use the trace() context manager, custom_span(), and manual span lifecycle to build detailed, hierarchical trace visualizations for complex multi-step agent workflows.
