Course tracks

Build a cinematic, responsive, accessible, search-ready website from a real client brief through design system, implementation, performance-safe interaction, deployment, handoff, and portfolio evidence.

Build a real production-style AI web application from a defensible product specification through frontend, backend, database, authentication, testing, deployment, and portfolio evidence.

Core data science and machine learning foundations — the layer every AI specialization above is built on.

Working inside Claude Code as an AI-native development environment — from setup to autonomous multi-step builds.

How to design AI systems that plan, decide, and act across multi-step tasks instead of just answering prompts.

Foundational to advanced generative AI — how these models work and how to build real applications on top of them.

Amazon's AI/ML stack in production — Bedrock, SageMaker — with a direct path to the AWS Certified AI Practitioner exam.

Product management for AI-native products — PRDs, evals, and roadmapping when the core feature is a model, not a form.

Building and deploying on Google Cloud's AI stack — Vertex AI, Gemini, and production ML pipelines.

Building and certifying on Microsoft's AI stack — Microsoft Foundry, Azure OpenAI, and AI-900/AI-103 certification prep.

A ground-up map of the modern AI engineering stack — models, orchestration, retrieval, and deployment — as one connected system.

Turning trained models into reproducible, monitored, production-grade ML systems.

Quality engineering for AI systems — testing non-deterministic LLM and RAG outputs the way QA tests deterministic code.

Using AI to automate IT operations itself — anomaly detection, alert correlation, and self-healing infrastructure.

The production framework stack for building controllable, stateful multi-agent applications.

Where classic data science meets generative models — RAG, fine-tuning, and LLM-powered analytics.

Applying agentic AI to the DevOps lifecycle — incident response, deployment automation, and infrastructure monitoring.

Building and selling production AI agents visually — no Python required — using n8n as the orchestration layer.

Operationalizing large language models specifically — prompt versioning, evaluation, cost, and deployment at scale.

Defending LLM applications and agents against prompt injection, jailbreaks, and the OWASP Top 10 for LLMs.

How FDEs take AI from a working demo to something that survives inside a real customer's messy enterprise environment.