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
Create a fully typed MCP server in TypeScript using the official MCP SDK, with tool handlers, Zod validation, and deployment strategies for exposing Node.js services to AI agents.
Learn how to build an AI agent that schedules medical appointments with provider matching, slot optimization, and HIPAA-compliant data handling. Includes EMR integration patterns and encryption strategies.
Build an AI agent for medication adherence that handles reminder scheduling, drug interaction checking, refill tracking, and caregiver notifications — with practical Python implementation.
Build an AI agent that transcribes meeting audio, generates structured summaries with key decisions, extracts action items with assignees, and distributes notes to participants automatically.
Build developer tools for inspecting, visualizing, searching, and manually editing AI agent memory state, enabling effective debugging and testing of memory-dependent behavior.
Explore four approaches to building agent memory — in-memory lists, file-based storage, relational databases, and vector stores — with practical Python implementations and guidance on when to use each.
Learn how to build an AI agent that provides personalized menu recommendations based on guest preferences, dietary restrictions, allergen awareness, and intelligent food and drink pairings.
Learn how to build a Mixture-of-Agents (MoA) architecture that combines outputs from multiple LLMs using a proposer-aggregator pattern to produce higher quality results than any single model.
Build an AI agent that ingests monitoring alerts, classifies severity, executes runbook steps automatically, and escalates critical issues to on-call engineers.
