hubagenticai

learning path

Tutorials

Hands-on builds with runnable code, grouped by level. Want the full curriculum — tutorials, decision guides and playbooks in one order with progress tracking? Follow a learning track.

Beginner

New to agents, or used ChatGPT but never built one. Understand what an agent really is, then build one that works — a tool server, an agent loop, and an agentic coding workflow.

  1. 01 How an AI agent actually works: build the loop behind every framework Every agent framework wraps the same ~40-line loop: model decides, tool runs, result feeds back. Build it in plain Python and the whole ecosystem stops being magic. ⏱ 40 min
  2. 02 MCP vs. A2A vs. AG-UI: the agent protocol stack, explained with one diagram The three agent protocols solve three different problems — agent-to-tools, agent-to-agent, and agent-to-user. Learn which layer each owns and when you need more than one. ⏱ 25 min read
  3. 03 How to build your first MCP server, step by step (Python and TypeScript) Build a working Model Context Protocol server with tools and resources, connect it to a real client, and understand what actually happens on the wire. ⏱ 45–60 min
  4. 04 Claude Code from zero: an agentic coding workflow, step by step Install Claude Code, learn the core loop, and build up to a disciplined agentic workflow: CLAUDE.md, plan mode, custom skills, hooks, and MCP servers. ⏱ 50 min
  5. 05 How to write Agent Skills (SKILL.md) that work across coding agents A skill is a folder with a SKILL.md file that a coding agent loads only when it needs it. Build a working release-notes skill with a bundled script, put it where Claude Code, Codex, Copilot, Cursor and Gemini CLI can all find it, and fix it when it does not trigger. ⏱ 30 min
  6. 06 How to build a personal AI agent for daily productivity (note and task triage) Build an agent that triages your notes into tasks, references, and archives — runnable today with zero API keys, upgradeable to any LLM, and scalable from personal to team use. ⏱ 40 min

Intermediate

You’ve built a demo agent and want it to be reliable. Structured outputs, real integrations, memory, multi-agent orchestration, and evals — the engineering that turns a demo into a system.

  1. 01 Structured outputs for agents: make models emit JSON you can actually trust Agents break where prose meets code. Build the validate-and-retry loop that turns flaky model JSON into a reliable contract — in plain Python, runnable without an API key. ⏱ 35 min
  2. 02 How to wrap a REST API in an MCP server (without handing the agent the whole API) Turn any REST API into agent-safe MCP tools: a narrow allowlist instead of a proxy, PII redaction before the model sees data, and a fake API so you can test the whole thing offline. ⏱ 45 min
  3. 03 How to migrate an MCP server to the stateless 2026 spec (mcp v2 and TypeScript SDK v2) `pip install mcp` now gives you mcp 2.x and your FastMCP import breaks. Move a working MCP server to the stateless 2026-07-28 spec in Python and TypeScript, without locking out the clients that still use the old protocol. ⏱ 45 min
  4. 04 Agent memory patterns: vector stores, knowledge graphs, and context engineering Why agents forget, the four memory patterns that fix it, and a working retrieval loop you can run in plain Python before you buy a vector database. ⏱ 40 min
  5. 05 Multi-agent orchestration explained: build an orchestrator and sub-agents from scratch Build the agent harness pattern in ~80 lines of plain Python — an orchestrator that plans, delegates to specialist sub-agents, and synthesizes — with a mock model so you can run it instantly. ⏱ 50 min
  6. 06 How to evaluate an AI agent: build a golden-task eval harness from scratch Agents without evals break silently on every prompt tweak. Build a small golden-task harness in plain Python — tasks, checks, scoring, and a regression gate you can run in CI. ⏱ 60 min

Advanced

You run agents for a team or company — or will soon. Security, human oversight, observability, cost control, and governance for agents doing real work in production.

  1. 01 How to trace AI agents with OpenTelemetry (agent, LLM, and tool spans) Instrument a small Python agent loop with the OpenTelemetry GenAI semantic conventions: one invoke_agent span per run, a chat span per model call, an execute_tool span per tool call, plus token usage and errors. Then use the trace to explain what a run cost and where its time went. ⏱ 45 min
  2. 02 Run agents locally: LLM serving plus MCP on your own hardware Serve an open-weights model with llama.cpp on your own machine (ARM64 included), expose an OpenAI-compatible endpoint, and wire a local agent loop to MCP tools — no cloud required. ⏱ 60–90 min

newsletter

One practical agentic-AI guide in your inbox. No news, no hype.

Tutorials and decision frameworks as they ship. Unsubscribe anytime.

Quick Jump:
↑ ↓ navigate ↵ select esc close
hubagenticai engine