Learn AI / Learning Paths /From prompts to agents
From prompts to agents
How a system that answers becomes a system that acts, and what has to be supervised when it does.
Prompt
The text, image or other input that guides a model on what kind of output to produce next.
System prompt
A high-priority instruction that sets the assistant’s role, rules and priorities before it responds to later messages.
Prompt engineering
The practice of writing and refining instructions so a language model is more likely to produce a useful, safe and well-structured reply.
In-context learning
A model uses examples and instructions placed in the current prompt to imitate a pattern for that one interaction, without changing its stored parameters.
Tool use
A system uses external software or devices during a task to look up information, calculate, carry out actions or control equipment beyond its own processing.
Function calling
A method that lets a model return a structured request for an external tool or system instead of only producing free-form text.
AI agent
An AI system that can pursue a goal by selecting and carrying out multiple steps, often using software tools, with oversight matched to its risks.
Orchestration
The control layer that coordinates an AI system’s steps, tools, rules and handoffs so a task can move from request to checked result.
Human in the loop
A system setup where a person reviews, guides or approves an AI-driven step before the workflow continues or completes.