47 lines
1.6 KiB
Markdown
47 lines
1.6 KiB
Markdown
# What Is an AI Agent, Really?
|
|
|
|
**June 2, 2026**
|
|
|
|
An AI agent = LLM + Tools + Loop. If any of the three is missing, it is not an agent.
|
|
|
|
## The Three Components
|
|
|
|
**LLM** — The reasoning engine. Given context and available tools, it decides what to do next. The LLM is NOT the agent. It is the brain of the agent.
|
|
|
|
**Tools** — The capability surface. Functions the agent can call: read files, run commands, search the web, query databases. Each tool has a name, description, and input schema.
|
|
|
|
**Loop** — The autonomous decision cycle. Think (LLM decides) leads to Act (tool executes) leads to Observe (result comes back) leads to Repeat.
|
|
|
|
## What Each Combination Gives You
|
|
|
|
| Combination | Result |
|
|
|-------------|--------|
|
|
| LLM only | Chatbot |
|
|
| LLM + Tools (no loop) | Augmented inference |
|
|
| LLM + Loop (no tools) | Talking to itself |
|
|
| LLM + Tools + Loop | Agent |
|
|
|
|
## The Loop in Pseudocode
|
|
|
|
```python
|
|
messages = [system_prompt, user_request]
|
|
while True:
|
|
response = llm.invoke(messages, tools=tool_definitions)
|
|
if response.is_final_answer:
|
|
print(response.content)
|
|
break
|
|
tool_name = response.tool_call.name
|
|
tool_args = response.tool_call.args
|
|
result = execute_tool(tool_name, tool_args)
|
|
messages.append(response)
|
|
messages.append(result)
|
|
```
|
|
|
|
## Common Misconception
|
|
|
|
"The model is the agent." No. The model is the brain. The agent is the whole system: brain plus tools plus loop. A better brain helps, but better tools and a better loop help more.
|
|
|
|
---
|
|
|
|
*From Module 1 of the [Agentic Engineering Course](/). The full module includes your first lab: building a single-tool agent from scratch.*
|