Our New Agentic AI Engineering Course!

2026-02-17 · Source: What's AI by Louis-François Bouchard · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, short

Summary

Towards AI has launched a new course, "Agentic AI Engineering," designed to bridge the gap between basic LLM demos and production-ready AI agent systems. Developed by Lufran Bushar and Paul Eston, drawing from two years of client work with 15 AI engineers, the course focuses on equipping developers with the skills to build advanced agentic systems. It addresses the industry need for engineers proficient in memory, tool use, reasoning loops, data integration, workflow orchestration, evaluation, reliability, and deployment. Participants will construct a complete, production-ready multi-agent system, including a research agent and a multimodality writing agent, implementing planning loops, critique cycles, and context management. Upon completion, students receive a professional certification, a deployable portfolio project, and lifelong access to a private Slack community.

Key takeaway

For AI Engineers aiming to transition from basic LLM applications to robust, production-grade agentic systems, you should consider this course to acquire the necessary skills. It offers a structured path to develop expertise in critical areas like memory, tool use, and reasoning loops, enabling you to build deployable multi-agent solutions. This will position you as a high-demand professional capable of delivering complete AI solutions that integrate into existing systems and meet real-world user needs.

Key insights

Building production-ready AI agents requires extensive engineering beyond basic LLM calls.

Principles

• Models alone cannot perform real-world tasks.
• Engineering makes LLMs useful in products.

Method

The course teaches building multi-agent systems by implementing planning loops, critique cycles, workflow logic, tool use, memory, and context management to ensure reliable agent behavior.

In practice

• Build a research agent for information gathering.
• Develop a multimodality writing agent.
• Integrate agents for collaborative tasks.

Topics

• Agentic AI Engineering
• Multi-Agent Systems
• LLM Engineering
• Tool Use
• Context Management

Best for: AI Engineer, Machine Learning Engineer, Software Engineer

Related on AIssential

• From Backend Engineer to Building AI Agents: Week 1 — Building AI agents involves understanding LLM API simplicity and leveraging tool calling for real-world actions.
• Go from 'my agent runs' to 'it ships.' — Reliably building and deploying AI agents requires robust engineering practices, evaluation, and monitoring.
• 🥇Top AI Papers of the Week — LLM agents are evolving to reason compositionally, learn reusable skills, and operate more efficiently through code and structured memory.
• Fundamental knowledge SWE's in 2026 must have before I will even consider hiring them — Building an LLM agent involves a simple loop integrating specialized tools and careful context management.
• The Beginner’s Guide to Agentic AI: Building Your First AI Agent as an SDET — AI agents are an engineering pattern integrating LLMs with tools and feedback loops for autonomous goal achievement.
• The “wow demo” trap is killing LLM projects. Here’s the exit. — Transitioning from LLM demos to production requires structured learning in architecture, reliability, and full-stack implementation.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by What's AI by Louis-François Bouchard.