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
Learn when and how to run multiple LLM completions in parallel, including fan-out patterns, cost-speed tradeoffs, result selection strategies, and timeout handling for production AI agents.
Learn how to execute multiple tool calls in parallel to dramatically speed up AI agent workflows. Covers async execution with asyncio.gather, handling partial failures, result aggregation, and timeout management.
Learn the parent-child chunking strategy where small chunks provide precise search matches while their larger parent chunks provide the full context needed for accurate generation.
Build an AI agent that delivers personalized health education by retrieving condition-specific content, adapting reading levels, supporting multiple languages, and tracking patient comprehension.
Build an AI agent that automates patient intake by generating dynamic forms, verifying insurance eligibility, collecting medical history, and managing consent documents before the visit.
Build a PDF processing agent that extracts text, tables, and charts from documents using Python. Covers page-level parsing, table detection with pdfplumber, chart analysis with vision models, and structured output generation.
Learn how to install pgvector, create vector columns, build IVFFlat and HNSW indexes, and run similarity queries directly inside PostgreSQL without adding another database to your stack.
A hands-on guide to setting up Pinecone, creating serverless indexes, upserting embeddings, running similarity queries, and filtering results with metadata for production AI applications.
Master the Pipeline pattern for AI agents — design sequential processing stages with intermediate results, error propagation, and checkpointing for resilient multi-step workflows.
