This live online AI agent developer course does not just explain concepts — it produces working production code. By the end of the 6-hour session you have built a complete Glass-Box Context Engine: a production AI agent system with MCP orchestration, RAG, memory management, safeguards, and observability.
By Packt Publishing · Refunds up to 10 days before
Most online AI agent courses deliver knowledge. This course delivers a working production AI agent system. Denis Rothman guides you through every implementation decision during the live 6-hour session, producing code you can deploy immediately and a deep understanding of why every component is designed the way it is.
Context engineering is the discipline of designing systems that give AI the right information, in the right format, to reason and act reliably. It goes beyond prompt engineering — building structured, deterministic systems that scale in production.
A multi-agent system uses multiple specialised AI agents working together — each with a defined role, context, and tools — to complete complex tasks no single agent could handle reliably. Context engineering makes them predictable.
MCP is Anthropic's open standard for connecting AI models to tools, data sources, and other agents. It provides structured agent orchestration with clear context boundaries — making systems transparent and debuggable.
Context engineering requires hands-on practice to truly understand. This live workshop lets you build a working system with a world-class instructor answering your questions in real time.
Six modules. Six hours. A production-ready context-engineered AI system by the time you finish.
Understand why prompts fail at scale and how semantic blueprints give AI structured, goal-driven contextual awareness.
Design and orchestrate multi-agent workflows using the Model Context Protocol. Build transparent, traceable agent systems.
Build RAG pipelines that deliver accurate, cited responses. Engineer memory systems that persist context reliably across agents.
Architect a transparent, explainable context engine where every decision is traceable and debuggable in production.
Implement safeguards against prompt injection and data poisoning. Enforce trust boundaries in multi-agent environments.
Deploy your context-engineered system to production. Apply patterns for scaling, monitoring, and reliability.
Concrete working deliverables — not just theory and slides.
A working Glass-Box Context Engine with transparent, traceable reasoning
Multi-agent workflow orchestrated with the Model Context Protocol
High-fidelity RAG pipeline with memory and citations
Safeguards against prompt injection and data poisoning
Reusable architecture patterns for production AI systems
Certificate of completion from Packt Publishing
Denis Rothman brings decades of production AI engineering experience to this live workshop.
Denis Rothman is a bestselling AI author with over 30 years of experience in artificial intelligence, agent systems, and optimization. He has authored multiple cutting-edge AI books published by Packt and is renowned for making complex AI architecture concepts practical and immediately applicable. He guides you step by step through building production-ready context-engineered multi-agent systems — answering your questions live throughout the 6-hour session.
Intermediate to advanced workshop. Solid Python and basic LLM experience required.
Everything you need to know before registering.
After completing this course you will be able to build: production multi-agent AI systems with typed MCP orchestration, AI applications grounded in private knowledge bases through high-fidelity RAG, AI agents with persistent memory across long conversations, context-engineered AI systems with Glass-Box observability, and production deployments of these systems with appropriate safeguards and monitoring. These capabilities cover the majority of enterprise AI application use cases.
Self-paced online AI agent learning gives you flexibility but lacks the interactive debugging support, real-time architectural guidance, and live Q&A that accelerate learning through the hardest parts. This live course compresses months of self-paced learning into 6 hours by providing expert guidance exactly when you need it: when you hit implementation challenges, when you face architectural decisions, and when the component interactions are unclear. The live format is significantly more efficient for the complex, interconnected concepts in multi-agent engineering.
Yes. The Glass-Box Context Engine you build during this course is a substantive engineering artifact that demonstrates production AI engineering capability. It covers architectural design (Glass-Box, context engineering), protocol implementation (MCP), retrieval engineering (RAG), and production engineering (safeguards, observability, deployment). Participants regularly include their workshop implementation in professional portfolios as evidence of senior AI engineering skills.
The course uses Python as the primary language, the official MCP Python SDK for agent orchestration, standard embedding libraries for the RAG pipeline, Pydantic for typed data validation, Python's asyncio for async agent communication, and structured logging for the Glass-Box observability layer. The instructor covers environment setup at the start and ensures all participants have working environments before the first build module begins.
This online course is highly interactive during the live session: participants ask questions throughout (not just in a Q&A block at the end), the instructor addresses implementation issues as they arise in real time, participants share their screens when they encounter problems, and the pace adjusts based on the group's progress. The live format is intentionally different from a recorded lecture — it is a guided build session with expert support available throughout.
If you register but cannot attend the live session, you receive the complete recording immediately after the workshop. The recording captures the complete build sequence and all Q&A from the live session. Many participants watch the recording at their own pace and implement alongside it — they report this approach is highly effective because they can pause and rewind at their own learning speed. A reference implementation is also provided for comparison.
6 hours. Bestselling AI author. Production context-engineered multi-agent system by the end. Seats are limited.
Register Now →Saturday April 25 · 9am to 3pm EDT · Online · Packt Publishing · Cohort 2