Checked fact 123212 Oct 2026Agents and apps

The Agent SDK documentation says that when you start an agent, Claude evaluates the prompt, calls tools to take action, receives the results, and repeats until the task is complete.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

When you start an agent, the SDK runs the same execution loop that powers Claude Code: Claude evaluates your prompt, calls tools to take action, receives the results, and repeats until the task is complete.

What the source said when we opened it, on 12 Oct 2026.

The source

How the agent loop works
Claude Code documentation

Open the source archived copy

Checked

Checked by the notis newsroom on 12 Oct 2026, against the source above.

In the story

How an agent harness runs a model and enforces limits 12 Oct 2026

Cite this fact

Short permanent address

In a sentence

“The Agent SDK documentation says that when you start an agent, Claude evaluates the prompt, calls tools to take action, receives the results, and repeats until the task is complete.” ai notis, checked 12 Oct 2026. Source: How the agent loop works (Claude Code documentation). https://ainotis.com/c/1232

As a reference (APA style)

ai notis. (2026, October 12). The Agent SDK documentation says that when you start an agent, Claude evaluates the prompt, calls tools to take action, receives the results, and repeats until the task is complete [Checked claim 1232]. ai notis. https://ainotis.com/c/1232

Anyone may quote this address. It does not change; if we correct the story, this page says so.