# ReAct: Reason, Act, Observe — AI Agents and Tool Use

Source: https://www.geekswithgeeks.com/en/ai-agents-mcp/found-react

> Follow the ReAct pattern where the model alternates short reasoning with tool actions.

## Think, then do, then look

**ReAct** (Reasoning + Acting) interleaves a short **thought**, an **action** (a tool call) and an **observation** (the tool result), then repeats. Thinking about the observation before the next action helps the model correct course. Modern tool-calling APIs give you this loop structurally; the model can also reason before calling a tool.

## A ReAct transcript

Older text-only agents asked the model to print these lines and parsed them. The parsing line below ran as shown: it pulls the tool name and JSON arguments out of the text.

```python
text = ("Thought: I need the balance.\n"
        "Action: get_balance\n"
        "Action Input: {\"account_id\": 7}")
fields = dict(l.split(": ", 1) for l in text.splitlines())
print(fields["Action"], json.loads(fields["Action Input"]))
```

Output:

```
get_balance {'account_id': 7}
```

## Prefer structured tool calls

Parsing free text breaks when the model changes wording. Native tool calling returns a validated name and JSON arguments, which is far more reliable than regular expressions on prose.

**Quiz:** What happens after an action in ReAct?

- [x] The model sees an observation and reasons about the next step
- [ ] The run ends
- [ ] The tools are deleted
- [ ] The user must restart

*Answer:* The model sees an observation and reasons about the next step. The observation feeds the next round of reasoning, which closes the loop.