A practical look at building voice agents in 2026. Realtime LLM APIs (OpenAI Realtime, Anthropic, Gemini Live), end-to-end latency, ASR and TTS, interruption handling, and the production patterns from real deployments.
When multi-agent systems beat single-agent, the supervisor / worker / reviewer / critic patterns, hierarchical vs swarm, communication models, evaluation, and the production patterns that survive contact with users.
How Claude Code Skills work, the SKILL.md format, when skills beat tools, multi-session workflows (writer/reviewer, fresh-context review), and the agentic coding patterns that ship real production code in 2026.
MCP from first principles — the protocol, transports (stdio, HTTP), tools/resources/prompts, why it works, and a concrete walkthrough of building an MCP server in Python and TypeScript.
A from-scratch tutorial on building AI agents with LangGraph. Tools, persistent state, conditional routing, human-in-the-loop, and the production patterns most demos skip.