Twelve weeks,
one real product
Every week is implemented hands-on in real code, in your choice of Python or TypeScript. The first three weeks build the fundamentals every AI engineer needs; the next nine assemble them into a working clone of a professional AI coding agent.
Foundations
The primitives of modern AI engineering: the agent loop, evaluation, and a production-grade runtime. Three weeks that most courses never reach.
Your First Agent
Build a general-purpose AI agent from scratch in nine parts — from a single tool call to a complete agent with evals, file, web and shell tools, context management and human approval. No frameworks.
Evals & Engineering Discipline
Build a diagram-design agent, put real evals around it, then make it measurably better — context engineering, sharper tools, RAG, richer output, human approval, and a data flywheel that turns every correction into a test.
The Runtime — Build a Harness
Build the layer that makes an agent survive production: durable execution that shrugs off crashes, a sandbox for model-written code, flat memory, least-privilege routing, parallel supervision, and human approval that can wait three days.
Build the Clone
One subsystem per week. Each week your tool — mycode — gains a real capability, and by Week 12 it reads codebases, edits files, plans, remembers, previews its work, traces itself, and orchestrates a team of sub-agents.
The Chat Interface
The capstone begins. Build a streaming terminal REPL with slash commands, safe interrupts and a live cost meter — the interface layer that makes an agent feel like a product.
Tools That Touch Code
A chatbot talks about your code; an agent changes it. Add the six tools that make a coding agent — read, write, edit, bash, glob, grep — plus the permission system that makes it safe to live with.
Context & Prompt Engineering
The highest-leverage week of the course. Assemble the system prompt, read project rules from an AGENTS.md the agent discovers itself, and survive long conversations by compacting without losing what matters.
RAG + Vector Databases
Grep finds exact strings; it cannot answer "where do we handle rate limiting?" when the code says throttle. Build a vector database from scratch — chunking, embeddings, cosine similarity, incremental re-indexing — and wire it in as a tool.
Planning & Agent Loops
An agent with tools but no plan overreaches on some tasks and quits early on others. Add a read-only plan mode, a todo list the agent maintains, feature lists the harness verifies, and a maker/checker loop.
Memory & Sessions
Close the terminal and a normal agent forgets everything. Add resumable session transcripts, persistent cross-project memory, and a handoff file so a fresh session continues exactly where the last one stopped.
Artifacts, Preview & Sandbox
Add artifact rendering and a live-preview server so generated pages refresh as the agent edits them, a background-task runner for long jobs, and a real OS-enforced sandbox so model-written code cannot touch what it should not.
Evals, Tracing & Reliability
Add full request tracing, cost and latency observability, an eval suite for your own agent, and the reliability patterns that let it recover from its own mistakes.
Multi-Agent Orchestration
Sub-agents, parallel orchestration and small focused agents — then final capstone assembly. By Friday you have a complete AI coding agent you built yourself.
By Friday of Week 12, you don't have notes. You have a tool.
A complete, working AI coding agent you built from scratch — and the deep understanding to explain every line of it.
Message me on LinkedIn →