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
Technical deep dive into agent memory architectures covering conversation context, vector DB persistence, and experience replay with implementation code for production systems.
Build production monitoring dashboards for AI agents tracking response latency, tool call success rates, token usage, cost per interaction, and SLA compliance.
Build real estate AI agents with multi-agent property search, suburb intelligence, mortgage and investment calculators, and automated viewing scheduling for PropTech platforms.
Microsoft autogen framework latest features 2026: autoGen deep dive covering conversable agents, group chat patterns, code execution sandboxing, human proxy agents, and custom agent types for production multi-agent systems.
How autonomous coding agents work in 2026 comparing Claude Code CLI, OpenAI Codex, and Cursor IDE with architecture details, capabilities, pricing, and real usage patterns.
Build a powerful AI coding assistant that reads files, runs tests, and fixes bugs using the Claude API and Model Context Protocol servers in TypeScript.
Technical guide to building AI agents that automate document processing — PDF parsing and extraction, email classification and routing, and spreadsheet analysis with reporting.
Step-by-step tutorial on building an MCP server in TypeScript, registering tools and resources, handling requests, and connecting to Claude and other LLM clients.
Head-to-head comparison of ElevenLabs Conversational AI and OpenAI Realtime API for building voice agents: latency, voice quality, pricing, languages, and function calling.
