What is Agentic AI? A Practical Introduction
Agentic AI systems plan, use tools and act towards a goal instead of just answering a prompt. How they work, where they help, and where they fail.
Category
Agentic AI
How AI agents work, where they help, how to build them, and how to keep them safe and useful.
AI Agents vs. Agentic Workflows: Which One Do You Need?
Workflows follow code paths you define; agents choose their own steps. Five workflow patterns, a decision table, and why you should start simple.
How AI Agents Use Tools: Function Calling and the Model Context Protocol (MCP)
LLMs only produce text; tools let them act. How function calling works, what MCP standardises, a minimal MCP server in Python, and the security rules.
What are Multi-Agent Systems? When One Agent Is Not Enough
Multi-agent systems split a goal across specialised AI agents. The main architectures, what they cost, and when a single agent is the better design.
Agentic AI for Science: From Chatbots to Autonomous Research Assistants
Why AI agents suit scientific work, what makes it hard, and what we learned building El Agente systems for quantum simulation and chemistry.
How to Evaluate and Secure AI Agents: Evals, Guardrails and Human-in-the-Loop
Agents are non-deterministic and can act on the world. A practical guide to building evals, spotting the main security risks, and adding guardrails.