LLM Agents Courses and Certifications

Learn AI Agents: Build LLM-Powered Agents | Scrimba

Learn how to build LLM-powered agents that can do multi-step reasoning and interact with its environment via functions and APIs.

• Scrimba
• 1 hour 57 minutes
• Self-Paced
• Paid Course

LLM Agents for Modeling Group Dynamics: Free Webinar

Explore how LLM-powered agents simulate group dynamics and how researchers compare their behavior with real human groups.

• Wolfram U
• 2 hours
• Self-Paced
• Free Online Course

Amazon Web Services;  Amazon

AWS SimuLearn: Build and Deploy Tools Using LLM Agents

Practice designing and deploying an AWS solution with LLM agents through AI customer simulations and a guided lab in the live AWS Console.

• AWS Skill Builder
• 1 hour
• Self-Paced
• Paid Course

Building Agents

451 ratings at Udacity

Build robust AI agents with tools, memory, structured outputs, web and database access, agentic RAG, and performance evaluation.

• Udacity
• 11 hours
• Self-Paced
• Paid Course

Donato Capitella

LLM Agents with ReAct: From Chain of Thought to Program-Aided Language Models

Explore the evolution of LLM agents through Chain of Thought, PAL, and ReAct frameworks, understanding how these technologies enable AI systems to reason and interact with external tools effectively.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

AI Agents with LangChain and LangGraph

49 ratings at Udacity

Build and evaluate AI agents with LangChain and LangGraph using memory, tools, RAG, multi-agent collaboration, and human oversight.

• Udacity
• 15 hours
• Self-Paced
• Paid Course

Building Agents with Core Bioinformatics Tools

Builds LangChain-powered LLM agents for biomedical research, with tool use, memory, retrieval, evaluation, and drug-repurposing workflows.

• Udacity
• 11 hours
• Self-Paced
• Paid Course

Data Science Festival

Simple and Constrained LLM Agents - Building Controlled AI Systems for Production

Explore building simple, constrained LLM agents for fintech, balancing control and generalizability while mitigating risks in complex production ecosystems.

• YouTube
• 46 minutes
• Self-Paced
• Free Video

CodeEmporium

Understanding LLM Agents - Differences Between LLMs and RAG Systems

Explore the fundamental differences between LLM Agents, traditional LLMs, and RAG systems through clear comparisons and practical insights into autonomous AI capabilities.

• YouTube
• 14 minutes
• Self-Paced
• Free Video

PyCon Israel

Unit Testing LLM Agents with Python

Discover practical techniques for unit testing LLM agents using Python frameworks to ensure reliable and expected behavior in AI development.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

Donato Capitella

Design Patterns for Securing LLM Agents Against Prompt Injection - Paper Review

Explore six security design patterns to defend LLM agents against prompt injection attacks with practical code examples and implementation guidance.

• YouTube
• 34 minutes
• Self-Paced
• Free Video

MLOps World: Machine Learning in Production

AI Red Teaming - Why and How to Jailbreak LLM Agents

Discover how adaptive multi-turn attacks jailbreak LLM agents and learn practical strategies for continuous red teaming, automated threat detection, and human-in-the-loop monitoring.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

Anyscale

Introducing Terminal-Bench - Evaluating LLM Agents in Realistic Terminal Settings

Discover Terminal-Bench, a challenging benchmark for evaluating LLM agents in real-world terminal environments, addressing gaps in current agent evaluation methods.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

MLOps.community

A-MEM: Agentic Memory for LLM Agents - April Reading Group

Explore the A-MEM system for LLM agents that dynamically organizes knowledge using a Zettelkasten-inspired approach, creating contextual memory networks that evolve over time to enhance agent performance on complex tasks.

• YouTube
• 58 minutes
• Self-Paced
• Free Video

Open Data Science

Beyond the Prompt - Architecting Reliable Enterprise LLM Agents

Discover how to architect scalable, safe LLM agents for enterprise environments with strategic framework selection, robust tool design, and human-in-the-loop safety measures.

• YouTube
• 26 minutes
• Self-Paced
• Free Video