Your Path to Agentic AI for Production

Become an Agentic AI Engineer who designs production-ready systems and leave with an AI agent portfolio that proves it.

To Agent or Not to Agent?

Most developers get stuck in three places when building agents. We teach you to navigate all three.

Agents Work Locally, Break in Production

Build two production agents, fully deployed
Build Research Agent and Writing Workflow with full evaluation systems, observability, and deployment pipelines. These are production templates you can adapt for market research, content & report generation, diagrams, documentation, or any domain where autonomous intelligence and automations with agentic patterns add value.
Not Sure When Agents Are Worth It

Master the decision framework
Learn to design workflows that stay maintainable as requirements evolve. Master when to use deterministic routing versus agent autonomy, when to keep humans in the loop, and the patterns that scale from prototype to production.
Skills Get Outdated Fast

Build mental models, not framework knowledge
We teach system design fundamentals from scratch, not just today’s frameworks. Graduate with two deployable agents, certification, and the engineering judgment to architect any AI system, regardless of which tools are trending next.

What You’ll Build

Two production agents and the complete engineering system through hands-on capstone projects.

Research Agent

Build an autonomous research system to synthesize structured research notes. You’ll implement:
- Multi-source data collection – crawl websites, GitHub repositories, and YouTube videos
- ReAct reasoning loops – iterative research patterns
- Tool orchestration – integrate Firecrawl, gitingest, Gemini, and Perplexity via function calling
- Multi-round research cycles – automated query generation and refinement
- Human-in-the-loop feedback – user-approved query workflows
Writing Workflow

Transform research into publication-ready content with multi-modal outputs. You’ll implement:
- Multi-modal generation – text, Mermaid diagrams, and images
- Chain-of-thought prompting – coherent long-form content generation
- Evaluator-optimizer patterns – automated quality control loops
- Orchestrator-worker architecture – context engineering for style control
- MCP-based editing tools – real-time collaboration with Cursor
- LangGraph workflows – production pipeline orchestration
Agent Architecture

Master the complete production stack for AI agents, from foundations to deployment. You’ll implement:
- Durable workflows – LangGraph’s functional API for stateful orchestration
- Custom evaluation frameworks – LLM judges and alignment scoring
- Opik monitoring – debugging and tracing non-deterministic behavior
- Production deployment – Docker, Cloud Run, CI/CD pipelines
- Authentication & state – Descope integration and Cloud SQL management
- Integration patterns – deploy to Cursor, Claude, or custom implementations

Build Your First Agent This Week

󠁯•󠁏 Own two agents, fully production-ready
󠁯•󠁏 Gain portfolio-ready skills with certification
󠁯•󠁏 Master fundamentals that outlast trends

Self-paced learning • Regular updates • Risk-free enrollment

Course Curriculum

1. Part 1: Foundations of Agents and Workflows

Lesson 1, Part 1: The AI Engineer & The Agent Landscape

Lesson 1, Part 2: Course Admin

Lesson 2: LLM Workflows vs. AI Agents -The AI Engineer’s Dilemma

Lesson 3: Context Engineering

Lesson 4: Structured Outputs

Quick Quiz 1

Lesson 5: LLM Workflow Patterns

Lesson 6: Tools

Lesson 7: Planning and Reasoning

Quick Quiz 2

Lesson 8: ReAct Practice

Lesson 9: RAG Focus

Lesson 10: Memory for Agents

Lesson 11: Multimodal Data

Quick Quiz 3

2. Part 2A: Building Agentic Systems; Preparing to Build our Central Research Agent and Writing Workflow

Lesson 12: Central Project: Scope & Design

Lesson 13: Agent Frameworks Overview & Comparison

Lesson 14: LLM Agent System Design Considerations and Framework

Running the Agents

Quick Quiz 4

3. Part 2B: Building Agentic Systems; Building our Central Research Agent

Lesson 15: Nova End-to-End Project Walkthrough

Lesson 16: Foundations of Agentic Systems with FastMCP

Lesson 17: Initial Data Ingestion and Tooling

Lesson 18: The Research Loop: Query Generation, Perplexity, and Human Feedback

Lesson 19: Final Outputs and Agent Completion

Quick Quiz 5

4. Part 2C: Building Agentic Systems; Building our Central Writing Workflow

Lesson 20: Brown End-to-End Project Walkthrough

Lesson 21: Behind the Scenes of Iterating AI Architectures with the Brown Writing Agent

Lesson 22: Implementing the Foundations of the Writing Workflow

Lesson 23: Reviewing and Editing Through the Evaluator-Optimizer Pattern

Lesson 24: Human-in-the-Loop Through MCP Servers

Lesson 25: Orchestrate and Integrate Our Capstone Agents

Quick Quiz 6

Lesson 26: End-to-End Demo: Generating a Course Lesson

5. Part 3: Evaluation, Observability, Optimizations, and Deployment

Lesson 27: Agent Observability with Opik

Lesson 28: Creating Datasets for AI Evals

Lesson 29: Defining the Evaluation Processes and Metrics Theory

Lesson 30: Evaluating the Writing Workflow

Quick Quiz 7

Lesson 31: Continuous Integration for AI Engineering

Lesson 32: Preparing For Deployment: Authentication and Docker

Lesson 33: Preparing For Deployment: Database and File Download/Upload

Lesson 34: Continuous Deployment for AI Engineering

Quick Quiz 8

6. Part 4: Instructions for Students Capstone Project and Certification

Part 4: Building Your Own MCP Server (To Receive Certification)

Part 4: Project Submission

Share your success and showcase your new skills!

7. Extra tools

AI Tutor – Ask any question!

How It Works

Project-based learning designed for working professionals—self-paced with live instructor support.

Self-Paced + Live Introductory Cohort Calls: Learn on your schedule with lifetime access. Join introductory cohort calls with instructors and fellow course takers.
Learn by Building: Hands-on projects from day one. Build two production agents from scratch, not toy examples or follow-along tutorials.
Active Discord Community: Get unstuck fast. Connect with fellow builders, share progress, and collaborate on projects in an active engineering community.
Certificate Upon Completion: Prove you built and deployed production AI. Graduate with certification backed by two real systems—portfolio-ready proof you ship.
Lifetime Access + Updates: All current content plus future updates as AI evolves. Your investment stays valuable.
Money-Back Guarantee: 30-day full refund, no questions asked. Risk-free enrollment.

Who This Course Is For

Serious learners who want to sweat a bit and build cool shit.

Python: Comfortable with functions, classes, and API calls
LLMs: Familiar with OpenAI/Claude APIs and basic prompting
Docker & Cloud: Understand containerization and deployment basics
Skill Level: Intermediate to advanced, expect a challenge
Mindset: Learn by building, not watching tutorials

Brought to you by

Towards AI’s mission is to make “building with AI” more accessible.
Since 2019, we have helped teach over 400k about AI with our courses, blogs, tutorials, books, community, and personalized consultancy.

After shipping 21 AI apps, Paul Iusztin has used his best-selling LLM Engineer’s Handbook, Decoding AI Magazine, and social media platforms to lead 162,000+ AI engineers out of “demo purgatory” and into production-grade engineering.