Agent Fundamentals for AI Engineers
Agent fundamentals cover the loop in which a model chooses an action, calls a tool, reads the result and repeats until the task is done. The unit separates fixed workflows from open-ended agents and teaches how to design tool functions with clear names and schemas. It is where the AI Engineer path moves from answering to acting.
Stage: Agents and Tool Use · Part of the AI Engineer roadmap · Last reviewed 19 November 2026
What to learn in Agent Fundamentals
- Implement a loop that executes tool calls until the model returns a final answer
- Write a tool schema with a precise description and typed parameters
- Choose between a fixed workflow and an autonomous agent for a given task
- Set a maximum step count and stop conditions to prevent runaway loops
- Return tool errors in a form the model can use to recover
Agent Fundamentals interview questions
When is a deterministic workflow better than an autonomous agent?
When the steps are known in advance, such as extract, classify then store. A workflow is cheaper, faster, easier to test and more predictable. An agent is justified only when the number or order of steps depends on intermediate results that you cannot list beforehand.
What makes a tool definition easy for a model to use correctly?
A specific name, a description saying when to use it and when not to, narrowly typed parameters with enums where possible, and a concise structured result. Vague or overlapping tools lead to wrong selections and malformed arguments.
Where Agent Fundamentals fits in the AI Engineer roadmap
Agent Fundamentals belongs to the Agents and Tool Use stage (intermediate level), which takes about 84 hours. Software that acts.
Other units in this stage
Back to the full AI Engineer roadmap