AI Agents
Also known as: LLM agents, Autonomous agents
LLMs that loop: plan → call tools → observe results → repeat until done.
Autonomous systems that use LLMs as reasoning engines to plan, decide, and execute multi-step tasks. Typically combine tool use, memory, and planning loops (e.g. ReAct, function calling).
In practice
The fastest-growing interview area. Expect questions on ReAct vs function calling, planning failures, and how you'd evaluate an agent.
How it compares
Agents are the systems doing the work; MCP is one standard for how they call tools.
Comparisons that include AI Agents
Related topics
Questions that mention this term
- Why must agent generated code execute in an isolated sandbox, and what are e2b and Modal's isolation models?
- Explain precisely why a chatbot with persistent memory is not an agent
- Flashcard: why break a complex goal into subtasks before acting?
- Flashcard: what is an agent 'trajectory' and why does it matter for evaluation?
- Where should an agent scratchpad live in the context, and what gets pruned from it each iteration?
- Describe the three tier memory hierarchy used by modern LLM agent systems
Related terms
Agent Loop
The runtime: LLM call → tool call → observation → LLM call → … until a final answer or step cap.
Chain-of-Thought (CoT)
Ask the model to think step by step before answering. It boosts accuracy on reasoning tasks.
Context Rot
Long-running chats degrade: early instructions get forgotten, and tool calls become less reliable.
Function Calling
The model emits structured JSON specifying a tool call instead of free text; the host executes it.
In-Context Learning (ICL)
Show the model a few examples in the prompt and it learns the pattern, no fine-tuning needed.
Model Context Protocol (MCP)
An open protocol (from Anthropic) for letting LLMs call tools and read resources from any compatible server.