Build the AI coding agent
everyone else just uses.
A hands-on mentorship for engineers who are serious about AI. We start from the fundamentals — the agent loop, evals, a production runtime — and finish with a real AI coding tool you built yourself. Every subsystem, real code, no frameworks, no hand-waving.
Most engineers use AI tools. Very few can build one.
There is a widening gap in this field. On one side, developers who call an API and wire up a framework. On the other, engineers who understand what happens between the prompt and the answer — who can debug a runaway agent loop, explain why a tool call failed, cut a token bill in half, and prove a change made things better.
The second group is small, and it is what companies are actually hiring for. The fastest way into it is not another tutorial. It is building the thing yourself, once, properly.
If you build a working clone of a professional AI coding agent — the kind you already use every day — you will understand this field better than almost anyone who only consumes it. That is the entire course.
What you have by Week 12
Not notes. A tool — a complete AI coding agent, built one subsystem per week.
Streaming chat REPL
A terminal interface with slash commands, safe interrupts and a live cost meter.
A real toolset
Read, write, edit, bash, glob and grep — behind a permission system you trust.
Semantic code search
A vector database you wrote yourself: chunking, embeddings, incremental indexing.
Context engineering
Assembled system prompts, project rules from AGENTS.md, and compaction that survives long sessions.
Planning & restraint
Plan mode, a maintained todo list, and a harness that decides what "done" means.
Durable memory
Resumable sessions, cross-project memory, and clean handoffs between days.
A secure sandbox
OS-enforced limits and a directory jail, so model-written code cannot hurt you.
Tracing & evals
Full request tracing, cost and latency observability, and a regression suite you own.
Multi-agent orchestration
Sub-agents with narrow toolsets, running in parallel and merging cleanly.
Twelve weeks, one real product
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 — three weeks most courses never reach.
Build the Clone
One subsystem per week. Each week your tool gains a real capability.
The rhythm of every week
Read the handout
A designed, self-contained handout for the week — concepts, code, and the reasoning behind each decision.
Build it yourself
Every part is a runnable checkpoint. You type the code; nothing is copy-paste theatre.
Study the real thing
We open the actual Claude Code source and compare your subsystem to the production one.
Prove it works
Evals, tracing and measurement — so improvements are demonstrated, not claimed.
A recurring feature of the handouts. After you build a subsystem, we open the real Claude Code implementation and study the decisions a production team made — the constants they picked, the edge cases they hit, the comments they left behind. Building a demo is easy; the gap between a demo and a product is exactly what those sections are about.
Who this is for
✅ A good fit if you…
- Write Python or TypeScript comfortably
- Have used an AI coding tool and wondered how it works
- Want depth, not another API tutorial
- Are moving into AI engineering and need a portfolio project
- Prefer building the primitive over configuring the framework
✋ Not a fit if you…
- Want to train or fine-tune models (this is systems, not research)
- Are looking for no-code or prompt-only workflows
- Want a finished template to ship this weekend
- Cannot commit ~6 hours a week to building
Pouria Jahandideh
AI Engineer · Engineering Team Lead · 10 years building production systems
I build AI agents professionally — voice agents, an AI tax-preparation product, and ML tooling for medical imaging — and before that I spent a decade as a full-stack engineer and team lead across fintech, ride-hailing at 40M-user scale, and telecom e-commerce used in 10,000 stores.
I have also been teaching that whole time: I designed a full-stack curriculum and mentored hundreds of students through JavaScript, React, Python, Linux, DevOps and Kubernetes. This course is what I wish had existed when I started building agents.
Frequently asked
Do I need machine learning experience?
No. This is an engineering course, not a research course. You will not train models — you will build systems around them. If you can write Python or TypeScript comfortably and understand HTTP APIs, you are ready.
Which language do I write in?
Your choice — every code sample comes in both Python and TypeScript. Pick one track and stay on it. We use the raw official SDK, so both tracks read almost identically.
Why no frameworks?
Because frameworks hide exactly the parts you are here to learn. An agent loop is about forty lines of code. Once you have written it yourself, every framework becomes readable — and you can debug the ones you do adopt.
How much time per week?
Roughly 5–10 hours of hands-on building, depending on the week. Week 2 is the heaviest at around ten hours; most weeks land near six.
What do I actually have at the end?
A complete, working AI coding agent you built yourself — streaming chat, a full toolset, semantic codebase search, planning, memory, a secure sandbox, tracing and multi-agent orchestration. It goes in your portfolio, and you can explain every line of it.
Is this cohort-based or self-paced?
It is a mentorship — you get the handouts, the build, and direct access to me for review and unblocking. Message me on LinkedIn to talk about timing and fit.
Ready to build the thing everyone else just uses?
By Friday of Week 12 you do not have notes. You have a tool — and the deep understanding to explain every line of it.
Message me on LinkedIn →Message me to talk about timing, fit and pricing. I reply to everyone.