Everyone's talking about AI adoption. Almost nobody has the real numbers. Help us change that โ€” and get the full report ๐Ÿ‘‰ Engineers | Leaders

Software Developer

9 courses ยท ~40 hoursยท 5 certifications available

phase 1 โ€” Understand the mechanism

Learn how AI coding tools actually work under the hood.

[ ] Understanding Tool Calling

This is how Cursor, Copilot, and every AI coding tool works under the hood.

4 sections ยท 10 lessons
  • [ ] Foundations (2 lessons)
  • [ ] How Models Decide (2 lessons)
  • [ ] Advanced Patterns (3 lessons)
  • [ ] Security and Production (3 lessons)
[โ†’ start course]

phase 2 โ€” Build your own agent

Build a working coding agent from scratch.

[ ] Building Your Own Coding Agent

You'll write ~200 lines of Python that do what Cursor does. Then you'll understand Cursor.

4 sections ยท 10 lessons
  • [ ] Getting Started (2 lessons)
  • [ ] The Conversation Loop (2 lessons)
  • [ ] Adding Tools (3 lessons)
  • [ ] Making It Real (3 lessons)

certification: Certified AI Agent Builder

[โ†’ start course]

phase 3 โ€” Master context

Learn what separates hobby agents from production agents.

[ ] Context Engineering

This is what separates hobby agents from production agents.

8 sections ยท 25 lessons
  • [ ] Tokens and Inference (2 lessons)
  • [ ] The Real Size of Your Context Window (4 lessons)
  • [ ] Anatomy of the Messages Array (5 lessons)
  • [ ] Dynamic Allocation: Tool Calling (2 lessons)
  • [ ] The Ralph Wiggum Loop (3 lessons)
  • [ ] Sub-Agents: Managed Runtimes for AI (3 lessons)
  • [ ] Message Passing: The Erlang OTP of AI (3 lessons)
  • [ ] Context Management Strategies (3 lessons)

certification: Certified Context Engineer

[โ†’ start course]

phase 4 โ€” Master the fundamentals

Build rock-solid CS foundations โ€” data structures, algorithms, and systems knowledge.

[ ] Data Structures & Algorithms

Arrays, linked lists, trees, graphs, sorting, dynamic programming โ€” the foundations that make everything else possible.

9 sections ยท 30 lessons
  • [ ] Arrays & Dynamic Arrays (3 lessons)
  • [ ] Linked Lists (3 lessons)
  • [ ] Stacks & Queues (3 lessons)
  • [ ] Hash Tables (3 lessons)
  • [ ] Trees & Traversal (3 lessons)
  • [ ] Binary Search Trees & Heaps (4 lessons)
  • [ ] Sorting Algorithms (4 lessons)
  • [ ] Graphs (4 lessons)
  • [ ] Algorithm Design (3 lessons)

certification: Certified in Data Structures & Algorithms

[โ†’ start course]
[ ] Computer Science Fundamentals

How CPUs work, caching, concurrency, networking, and complexity theory โ€” the systems knowledge that separates senior engineers.

8 sections ยท 21 lessons
  • [ ] How Computers Process Programs (3 lessons)
  • [ ] Caches (2 lessons)
  • [ ] Processes & Threads (3 lessons)
  • [ ] Networking (3 lessons)
  • [ ] Tries & String Searching (2 lessons)
  • [ ] Combinatorics, Probability & Information Theory (3 lessons)
  • [ ] NP-Completeness & Complexity Classes (2 lessons)
  • [ ] Advanced Data Structures (3 lessons)

certification: Certified in Computer Science Fundamentals

[โ†’ start course]
[ ] Software Design & Systems

Design patterns, testing, and system design โ€” the engineering practices that turn working code into well-engineered software.

7 sections ยท 20 lessons
  • [ ] Creational Design Patterns (3 lessons)
  • [ ] Structural Design Patterns (2 lessons)
  • [ ] Behavioral Design Patterns (3 lessons)
  • [ ] Testing (3 lessons)
  • [ ] System Design Fundamentals (3 lessons)
  • [ ] System Design Practice (3 lessons)
  • [ ] Computer Security & Parallel Programming (3 lessons)

certification: Certified in Software Design & Systems

[โ†’ start course]

phase 5 โ€” Go deeper [optional]

Optional deep dive into transformer architecture.

[ ] Understanding Transformers [preview]

Not required, but understanding attention helps you write better prompts and debug model behavior.

2 sections ยท 4 lessons
  • [ ] Attention Mechanisms (3 lessons)
  • [ ] Embeddings (1 lesson)
[โ†’ start course]
[ ] Understanding Micrograd

Build the autograd engine and neural network that power every ML framework โ€” from Value objects to gradient descent.

5 sections ยท 13 lessons
  • [ ] The Big Picture (2 lessons)
  • [ ] The Value Class (3 lessons)
  • [ ] Building a Neural Network (3 lessons)
  • [ ] Training (3 lessons)
  • [ ] The Full Picture (2 lessons)
[โ†’ start course]
[ ] Understanding Makemore

From bigram counting to WaveNet โ€” build character-level language models that generate names, learning the training techniques that preceded transformers.

5 sections ยท 15 lessons
  • [ ] Bigrams (4 lessons)
  • [ ] The MLP Language Model (3 lessons)
  • [ ] Activations and Batch Normalization (3 lessons)
  • [ ] Becoming a Backprop Ninja (3 lessons)
  • [ ] Building a WaveNet (2 lessons)
[โ†’ start course]

key terms

Tool CallingยทAgentยทContext EngineeringยทSystem PromptยทFinite-State MachineยทAgent HarnessยทArrayยทHash TableยทGraphยทBig-O NotationยทDesign PatternยทSystem DesignยทUnit Test

related reading

โ†’ Pi: the architecture of an AI coding agent

โ†’ Beads: the architecture of a graph issue tracker for AI agents