The promise

You build a real AI agent from scratch and understand every piece of it. Not theory. Not a wrapper around a framework. You write the loop, the tools, the memory, and the trace yourself — so when an agent misbehaves, you know exactly where to look. Then you give it real capabilities, ship it behind an API, connect it to MCP servers, teach it reusable skills, and engineer reliable autonomous loops.

Six workshops. One coherent journey. Every session ends with something you built.

The cohort runs as one eight-week arc. Foundations is weeks 1-4 and Intermediate is weeks 5-8 — take either on its own, or the Complete Journey for both.

Everything runs on your own machine with a local model — no API key and no bill while you learn.

"If you can't build it from scratch, you don't understand it."

The arc

Build → Empower → Ship → Connect → Extend → Engineer

WEEKS 1-4 — FOUNDATIONS
  W1  Build It        streaming agent + 3-file memory
  W2  Empower It      filesystem/terminal tools + safety
  W3  Ship It         web/email tools + FastAPI + client
      Capstone Day    build and present your own project

WEEKS 5-8 — INTERMEDIATE
  W4  MCP             agent as a client to any server
  W5  Skills          package your own capabilities
  W6  Loop + Prod     loop engineering, eval, responsible use
      Demo Day        present what you engineered

Each workshop ends with a concrete working project — not "you understood X," but "you built X."

The six workshops

W1 — Build It

"An agent without memory is just a fancy autocomplete."

Build the agent from scratch: the model talks → streams → uses tools → runs the loop → remembers you across restarts via three plain Markdown files.

Deliverable: a streaming, tool-using, memory-keeping agent (CLI) with a capstone file you can point to and say "this is what I built today."

W2 — Empower It

"You're the architect — the LLM is your junior dev."

Give the agent real power: read/write files, run commands, and even write and run its own code — all behind a safety model you control.

Deliverable: an agent that acts on real files and self-corrects, safely.

W3 — Ship It

"If it doesn't run behind an endpoint, it's a toy."

Give the agent web tools and an email tool, then put it behind a FastAPI endpoint with a streaming client.

Deliverable: a locally served agent application with an HTTP API and a working client.

W4 — MCP (week 5)

"Stop building tools. Start connecting."

Your agent becomes a client to any MCP server — borrowing tools it never had to write.

Deliverable: an agent powered by external MCP servers.

W5 — Skills (week 6)

"A tool is an appliance; a skill is a recipe."

Package tools into reusable skills — SKILL.md recipes the agent loads on demand to do a whole job.

Deliverable: an agent with a skill library.

W6 — Loop Engineering + Production (week 7)

"Stop prompting your agent — design the loop that prompts it."

Grow the W1 loop into a self-verifying goal-seeking engine with termination logic, budgets, evaluation, and ethics.

Deliverable: a production-pattern, self-driving agent with measurable quality.

Who this is for

• Basic Python required — functions, dictionaries, loops, terminal usage. Rusty rather than new to it? Every registration includes my full Python course free, so you can shore the basics up before week 1.
• No previous AI-agent experience needed
• Works entirely with a local model (Ollama + qwen2.5) — no API key required to start
• "From scratch" refers to building without an agent framework — you still need basic Python experience

Register

Pick a package below and click Register to reserve your spot.

Build a Real AI Agent — From Scratch · Ayman Hamed | AI Architect & Instructor · Simple but Impactful.