Skip to main content

Agents for LLM and RAG Engineers

LLM agents are systems where a model decides which actions to take, calling tools such as search, code execution or APIs in a loop until a task is done. Designing them means defining tool schemas, managing state and memory, and choosing between fixed workflows and open-ended agent loops.

Stage: Adaptation and Agents · Part of the LLM and RAG Engineer roadmap · Last reviewed 19 November 2026

What to learn in Agents

Agents interview questions

What is function calling?

Function calling lets you describe tools with names and JSON schemas. The model returns a structured request naming a tool and its arguments, your code runs it, and you send the result back. The model never executes anything itself, which keeps control in your application.

When should you prefer a workflow over an autonomous agent?

Prefer a fixed workflow when the steps are predictable, because it is cheaper, faster and easier to test. Use an agent loop only when the path depends on intermediate results. Autonomy adds cost, latency and failure modes that need guardrails.

Where Agents fits in the LLM and RAG Engineer roadmap

Agents belongs to the Adaptation and Agents stage (advanced level). Beyond prompting.

Back to the full LLM and RAG Engineer roadmap