Academy

Core techniques — context, retrieval, structured outputs, fine-tuning, and multimodal

12 chapters ~4.3 hr

Free

Claude Code

From first steps to power-user — master Claude Code inside and out

7 chapters ~2 hr

AI Engineering: Foundations

Build AI systems — foundational techniques, agent frameworks, specialized archetypes, and edge deployment

Agent Engineering

Agent primitives — tool use, memory, skills, MCP, retrieval, and failure recovery

8 chapters ~2.7 hr

Agent Infrastructure

The runtime substrate — sandboxing, interop protocols, memory backends, and orchestration primitives that production agents depend on

3 chapters 54 min

Agent Frameworks

Master the APIs and agent frameworks from OpenAI and Anthropic — from raw API calls to production agent systems

9 chapters ~3 hr

AI Engineering Foundations

Free

Core techniques — context, retrieval, structured outputs, fine-tuning, and multimodal

12 chapters ~4.3 hr

Data Engineering with AI

The pipeline half of the data world: dbt models, orchestrated DAGs, quality gates, broken-pipeline debugging, and warehouse cost, with agents in every loop.

7 chapters ~1.9 hr

Fine-Tuning & Distilling Open Models

From we should fine-tune to a governed loop: LoRA on open weights, distillation from frontier models, and the evals that prove it worked.

7 chapters ~2.1 hr

Run an LLM on Your Own Machine

FoundationsEngineer

Run a capable LLM on the computer you already own — pick a tool, fit a model to your hardware, serve it to real projects, and upgrade smartly when you outgrow it.

7 chapters ~2 hr

MCP Server Engineering

MCP servers are the new internal API. Build, secure, test, version, and operate one, practiced against a mock company API and mapped to your org.

8 chapters ~2.7 hr

On-Device & Edge AI

Ship AI where the user is — Apple Foundation Models, Gemini Nano, MLX, distillation, and edge deployment patterns

4 chapters ~1.3 hr

Specialized Agents

Production-ready agent archetypes — deep research, browser and computer use, voice, and scheduled autonomous ops

AI Engineering: Reliability & Trust

Ship, validate, and govern AI systems — production ops, code + E2E testing, evals, red-teaming, and compliance

LLM Evaluation

Evaluation as a discipline — from your first eval to LLM-as-judge rigor, eval suites at scale, and CI gating for production AI

Adversarial AI

Defend and red-team your AI — prompt-injection foundations, defense-in-depth, attack taxonomy, automated jailbreak tooling, and context poisoning for production systems

Code Testing for Agentic Dev

Static analysis, coverage, mutation, AI-driven test generation, pre-commit hooks, and property-based testing — the feedback loops that keep Claude Code and Codex honest

7 chapters ~2.4 hr

E2E & Multimodal AI Testing

Test what users experience — Playwright, agentic browser QA, LLM-powered visual and audio testing, and test infrastructure at scale

6 chapters ~2 hr

On-Call with AI

Fight ordinary production outages with AI agents: wire one into your telemetry, triage, debug live, verify the root cause, and decide exactly what it may touch in prod. All hands-on work runs on a provided lab.

8 chapters ~2.5 hr

Production AI

Ship and operate — testing, security, cost, streaming, system design, and UX

11 chapters ~3.8 hr

AI Coding Agents

Master the AI coding agents that are reshaping development — Claude Code, OpenAI Codex, Google Gemini CLI, Cursor, and the workflow craft that makes them effective

Google Antigravity

Master Google's agentic dev platform — the Antigravity desktop app, the agy CLI and SDK, migration from Gemini CLI, and the enterprise + cost tradeoffs

6 chapters ~1.7 hr

Free

Claude Code

From first steps to power-user — master Claude Code inside and out

7 chapters ~2 hr

Claude Code: Agents Orchestration

Multiply yourself across many Claude Code agents — subagents, worktrees, background sessions, agent teams, and dynamic workflows, and the judgment to pick the right one for the work in front of you

6 chapters ~1.9 hr

OpenAI Codex

Master OpenAI's coding agent — CLI, desktop app, IDE extension, and cloud tasks

Coding Agent Craft

The cross-vendor patterns and craft that make any coding agent — Claude Code, Codex, Gemini — produce reliable, mergeable output

10 chapters ~3.5 hr

A 2026 survey of every major AI coding agent — Claude Code, OpenAI Codex, Gemini CLI, GitHub Copilot, Cursor — with side-by-side comparison and decision frame for picking your stack.

Coding Agents Landscape

FoundationsEngineer

Cursor

Cursor IDE mastery — AI-native code editing, multi-file context, agent mode, and integration with your development workflow.

GitHub Copilot

Master GitHub Copilot end-to-end — chat, inline, edits, Workspace, PR review, custom instructions, extensions, memory, and enterprise governance

6 chapters ~2.1 hr

Legacy Code with AI: Understand, Modernize, Migrate

Most enterprise engineering is brownfield. Agents finally made it tractable: comprehension, safety nets, strangler slices, and migrations, practiced on a provided legacy codebase, applied to yours.

8 chapters ~2.7 hr

ML Engineering

Build models from scratch — classical machine learning with sklearn, then deep learning with PyTorch and TensorFlow. The model-building track, complement to the agent-systems work in AI Engineering.

Deep Learning

Deep learning in production — DL frameworks (PyTorch + TensorFlow), training techniques, vision tasks and CNNs, building from scratch vs transfer learning, and modern architectures.

Machine Learning

Classical machine learning fundamentals — algorithm selection, data preprocessing, exploratory analysis, feature engineering, model selection, and the sklearn algorithm families.

Open-Source AI

The open-weight world end to end — the model landscape, the enterprise adoption playbook, Kimi and GLM complete guides, coding on open backends, and serving open models in production

Coding on Open Models

Run the agent harness you already know on open backends (GLM, Kimi, DeepSeek, Qwen), measure the gap yourself, and route by task.

6 chapters ~1.5 hr

Serving Open Models in Production

Self-hosting as an engineering discipline: vLLM, GPU math, OpenAI-compatible gateways, observability, the honest cost model, and hardening a shared GPU across tenants.

7 chapters ~1.9 hr