Learning path · 11 parts
AI Agents Fundamentals
by MLHub Labs · 11 parts · about 226 min · intermediate
What an agent is, how the loop of thinking and acting works and when a simple workflow is the better choice.
Explore MLHub
Articles, learning paths and news on AI, machine learning and data science.
Learning paths
Tutorial series: every part of a topic, in order.
Articles
Machine Learning
Hands-On: An Agent in Plain Python, No Framework
Build a working tool-using agent from scratch in plain Python: the loop, a tool registry, error handling, a human approval …
MLHub Agents & Robotics Organization
21 hours ago • 30 min read
0
0
20
Machine Learning
Choosing a Framework, or None
A practical look at what agent frameworks actually do for you, the main categories on the market, and a decision …
MLHub Agents & Robotics Organization
5 days, 13 hours ago • 16 min read
0
0
59
Machine Learning
Human in the Loop
How to design checkpoints where a person reviews, approves or corrects what an agent wants to do, and how to …
MLHub Agents & Robotics Organization
1 week ago • 19 min read
0
0
46
Machine Learning
Errors, Retries and Stopping Conditions
Agents fail differently from normal programs: tools time out, models hallucinate arguments, and loops can run forever. Here is how …
MLHub Agents & Robotics Organization
1 week, 2 days ago • 25 min read
0
0
58
Machine Learning
Context Engineering
A practical look at what actually goes into an LLM's context window during an agent loop, why stuffing it with …
MLHub Agents & Robotics Organization
1 week, 4 days ago • 18 min read
0
0
83
Machine Learning
Memory: Short-Term, Long-Term and Notes
How agents remember anything at all: what lives in the context window, what gets stored for later, and why a …
MLHub Agents & Robotics Organization
2 weeks, 1 day ago • 24 min read
0
0
89
Machine Learning
Planning and Task Decomposition
Why breaking a goal into smaller, checkable steps often beats asking a language model to do everything in one go, …
MLHub Agents & Robotics Organization
2 weeks, 2 days ago • 21 min read
0
0
99
Machine Learning
Workflows Versus Agents
A clear line between code that decides what happens next and a model that decides for itself, with worked examples …
MLHub Agents & Robotics Organization
2 weeks, 4 days ago • 22 min read
0
0
82
Machine Learning
Tools and Function Calling
How a language model goes from predicting text to reliably triggering real actions: the mechanics of tool definitions, function calling …
MLHub Agents & Robotics Organization
2 weeks, 5 days ago • 17 min read
0
0
103
Machine Learning
The Agent Loop: Observe, Think, Act
A close look at the cycle that makes an AI agent an agent: how it observes its situation, decides what …
MLHub Agents & Robotics Organization
3 weeks ago • 21 min read
0
0
88
Machine Learning
What an Agent Is, and When You Do Not Need One
A clear, practical definition of an AI agent, built from two contrasting examples, plus a checklist for deciding when a …
MLHub Agents & Robotics Organization
3 weeks, 2 days ago • 13 min read
0
0
127
Latest News
All news-
NVIDIA's Nemotron 3.5 Super VL Lands on AWS: One Model for Text, Images and Video Agents
• 6 min read
-
AWS Publishes a Blueprint for Running AI Agents Safely Across a Whole Company
• 5 min read
-
How Exowatt's fine-tuned small models outperformed frontier AI on solar-plant tasks
• 6 min read
-
AWS shows how to manage thousands of per-camera vision models with SageMaker SDK v3
• 6 min read
Popular Posts
Types of Data: Categorical, Ordinal, Discrete and Continuous
3 weeks, 4 days ago • 17 min read
0 likes • 117 views • 1 comment
AWS shows how to manage thousands of per-camera vision models with SageMaker SDK v3
3 days, 20 hours ago • 6 min read
0 likes • 49 views • 0 comments
Colour Spaces: RGB, HSV and Greyscale
4 days, 21 hours ago • 15 min read
0 likes • 56 views • 0 comments
Recent Activity
Popular Tags
Stay Updated
Get the latest AI insights and tutorials delivered to your inbox.