3 phases · 25 modules · one capstone

Engineer AI agents that work in production.

Progress from Python and LLM fundamentals to multi-agent orchestration, safety, observability, and deployment—through a practical, end-to-end curriculum.

01Build
02Orchestrate
03Deploy

25

Practical modules

3

Progressive phases

1

Production capstone

100%

Project focused

Choose your phase

Select a phase to see what it covers.

Pick one of the three phases to preview its modules, then start learning when you are ready.

01

Phase 01

Foundations

Build the engineering base

Core Python, AI application tooling, LLM fundamentals, and retrieval—the building blocks every agentic engineer needs.

  • 01

    Python & AI Development Environment Setup

    Python projects, virtual environments, Git, secret management, and asynchronous LLM calls.

  • 02

    Building AI Apps with FastAPI, Streamlit & Gradio

    Build APIs, streaming chat interfaces, file pipelines, and shareable AI demonstrations.

  • 03

    LLM Fundamentals, Context & Prompt Engineering

    Tokens, context windows, structured outputs, function calling, and reliable prompt patterns.

  • 04

    Embeddings, Vector Databases & Semantic Search

    Create vector indexes, tune chunking, and combine semantic and keyword retrieval.

  • 05

    AI-Assisted (Vibe) Coding for Developers

    Use AI coding tools responsibly across planning, implementation, review, and debugging.

  • 06

    No-Code Workflow Automation

    Connect triggers, webhooks, agent APIs, and production-ready visual automations.

The learning journey

From first principles to production systems.

Open any module to see what you will build and practice. Each phase expands the capabilities of the one before it.

01

Phase 01

Foundations

Build the engineering base

Core Python, AI application tooling, LLM fundamentals, and retrieval—the building blocks every agentic engineer needs.

MOD-01

Python & AI Development Environment Setup

+

Python projects, virtual environments, Git, secret management, and asynchronous LLM calls.

MOD-02

Building AI Apps with FastAPI, Streamlit & Gradio

+

Build APIs, streaming chat interfaces, file pipelines, and shareable AI demonstrations.

MOD-03

LLM Fundamentals, Context & Prompt Engineering

+

Tokens, context windows, structured outputs, function calling, and reliable prompt patterns.

MOD-04

Embeddings, Vector Databases & Semantic Search

+

Create vector indexes, tune chunking, and combine semantic and keyword retrieval.

MOD-05

AI-Assisted (Vibe) Coding for Developers

+

Use AI coding tools responsibly across planning, implementation, review, and debugging.

MOD-06

No-Code Workflow Automation

+

Connect triggers, webhooks, agent APIs, and production-ready visual automations.

02

Phase 02

Orchestration & Protocols

Turn calls into systems

Chains, memory, agents, stateful graphs, evaluation tooling, and MCP transform isolated model calls into orchestrated systems.

MOD-07

LangChain Core — Chains, Memory & RAG

+

Compose reusable chains, memory strategies, retrievers, and grounded generation pipelines.

MOD-08

LangChain Agents & Tool Use

+

Build ReAct agents, typed tools, SQL integrations, retry logic, and streamed agent steps.

MOD-09

LangGraph — Stateful Workflows & Routing

+

Model agent state, conditional routes, nodes, edges, and deterministic control flow.

MOD-10

LangGraph — Cycles, Human-in-the-Loop & Persistence

+

Add review gates, checkpoints, resumability, fan-out, aggregation, and sub-graphs.

MOD-11

Tracing, Evaluation & Testing for LLM Applications

+

Trace runs, design datasets, measure quality, and prevent regressions.

MOD-12

Model Context Protocol — Architecture & Custom Servers

+

Build MCP tools, resources, prompts, transports, validation, and access controls.

MOD-13

MCP — Ecosystem Integrations

+

Connect agents to practical MCP services and manage multi-server environments.

MOD-14

Programmatic Prompting

+

Create declarative prompt programs, optimisers, metrics, and self-improving pipelines.

03

Phase 03

Production, Safety & Capstone

Engineer for the real world

Advanced agents, RAG, safety, observability, deployment, interoperability, and a complete production capstone.

MOD-15

Deep Agents — Reflection, Planning & Long-Term Memory

+

Design reflective loops, planning systems, memory layers, and context management.

MOD-16

Multi-Agent Orchestration & Custom MCP Servers

+

Coordinate specialist agents and build typed MCP servers from scratch.

MOD-17

Agentic RAG & GraphRAG

+

Build adaptive retrieval, corrective loops, knowledge graphs, and multi-hop reasoning.

MOD-18

Advanced Agentic Workflows with Visual Automation Tools

+

Combine visual workflows, webhooks, schedules, error branches, and LangGraph.

MOD-19

Guardrails & AI Safety

+

Apply input, output, and tool-use controls with policy-aware validation.

MOD-20

Monitoring, Evaluation & Fine-Tuning

+

Instrument traces and metrics, control costs, evaluate drift, and apply LoRA.

MOD-21

Containerising & Deploying AI Agents

+

Package services, automate CI/CD, secure containers, and perform blue/green releases.

MOD-22

Capstone Project, Part 1 — Architecture, Build & Integration

+

Choose a real problem, design the architecture, and integrate the complete system.

MOD-23

Capstone Project, Part 2 — Deployment

+

Deploy, monitor, audit, document, and demonstrate the live capstone system.

MOD-24

Agent Interoperability Protocols

+

Implement agent-to-agent communication, discovery, task delegation, and shared artifacts.

MOD-25

Generative AI and LLM Security

+

Defend against prompt injection, data leakage, insecure tools, and supply-chain risks.

Graduate outcomes

Leave with systems, not slides.

The course culminates in an integrated agent system you can deploy, observe, secure, and explain.

Orchestrated workflows

Build stateful, multi-step systems with routing, tools, persistence, and human review.

Production architecture

Connect APIs, RAG, agents, storage, and interfaces using maintainable engineering patterns.

Safety by design

Apply guardrails, evaluation, observability, security testing, and operational controls.

Deployable capstone

Deliver a documented live system with CI/CD, monitoring, performance, and security review.

Before you enroll

Frequently asked questions.

Prerequisites, time commitment, enrollment, and what each phase actually asks of you.

Course page & enrollment

Do I need prior experience with AI or machine learning?

+

No. Phase 1 starts from setup and fundamentals, so you do not need machine-learning theory, model training, or previous AI project experience. What helps is comfort with basic programming—variables, functions, loops—and using a terminal.

What should I know before I start?

+

Basic Python, or another language you can pick up quickly, plus a willingness to read documentation. Git, APIs, and command-line work appear early in Phase 1, and every module includes hands-on practice, so gaps get closed as you go rather than being assumed away.

How much time should I plan for each week?

+

Plan for around 6–8 hours a week: short lessons plus the hands-on build for that module. Learners who can only give a few hours a week still finish, but the capstone benefits from a longer, uninterrupted stretch near the end.

How long does the complete course take?

+

Most learners move through all three phases in roughly 12–16 weeks at a steady pace. The phases build in order—foundations, then orchestration, then production and the capstone—so the sequence matters more than the calendar.

How do I enroll, and where do I see pricing?

+

Enroll from the course page; every Learn now button on this site opens it. Current pricing, payment options, and what your access includes are listed there, and the syllabus details every module before you decide.

Can I start with Phase 2 or Phase 3?

+

The phases are ordered on purpose. Phase 2 assumes you can already build and call an application, retrieve context, and work with prompts. Phase 3 assumes you can orchestrate stateful workflows and evaluate them. If you already work with agents, the Phase 1 and Phase 2 module lists are the quickest way to check your gaps.

What happens in Phase 1: Foundations?

+

Six modules that turn setup into working software: a Python and AI development environment, APIs and chat interfaces with FastAPI, Streamlit, and Gradio, LLM fundamentals and prompt engineering, embeddings and vector search, AI-assisted coding practice, and no-code workflow automation. You finish with several small applications you built yourself.

What happens in Phase 2: Orchestration & Protocols?

+

Eight modules on turning isolated model calls into systems: LangChain chains, memory, and RAG; agents with typed tools; LangGraph workflows with routing, cycles, checkpoints, and human review; tracing, evaluation, and testing; the Model Context Protocol with custom MCP servers; and programmatic prompting. You finish with an orchestrated agent you can measure.

What happens in Phase 3: Production, Safety & Capstone?

+

Eleven modules on making it real: deep agents with planning and long-term memory, multi-agent orchestration, agentic RAG and GraphRAG, visual automation, guardrails and safety, monitoring and fine-tuning, containerizing and deployment, agent interoperability, and LLM security. It closes with a two-part capstone you design, build, deploy, and document.

Your path starts here

Study the complete 25-module curriculum.

Start learning today, or open the complete syllabus for every topic, hands-on exercise, skill, and capstone milestone.