> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sudoiq.com/llms.txt
> Use this file to discover all available pages before exploring further.

# What is an agent?

> Workflow graphs, versions, tools, and how you refer to an agent in API calls

An **agent** (also called a **workflow** or **graph** in the product) is a **versioned definition** of how work runs: which steps execute, in what order, how data flows between them, and which **tools** the model may call.

## Parts of an agent

| Concept                 | Meaning                                                                                                                                                                                                                                    |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Graph**               | Nodes (steps) and edges (control flow). One node is the **entry** where a run starts.                                                                                                                                                      |
| **Nodes**               | Typically include LLM calls, branching, tool use, and outputs.                                                                                                                                                                             |
| **Tools**               | Named capabilities the model can invoke. Names and JSON Schemas must be **registered** on the service so the graph can reference them.                                                                                                     |
| **Inference providers** | Agent nodes can run on multiple model backends, including **OpenAI**, **Anthropic**, **Google**, **Groq**, and **Baseten**. Depending on your deployment, plugin adapters can also route through **AWS Bedrock** or locally hosted models. |
| **Validators**          | Optional **output format** rules (JSON Schema) attached to nodes to validate structured outputs.                                                                                                                                           |
| **Version**             | Published graphs have a **version**; API calls can pin `agent_version` or use the default active version.                                                                                                                                  |

## From authoring to `agent_id`

The **easiest path** to creating a new agent is to use a **Sudoiq agent-builder**—either in the **product UI** or through the **`agentservice` CLI**—to design, iterate, and publish your workflow. If you prefer, you can pair the **CLI** (for example **`agentservice agents modify`**) with **your own coding agent** or editor workflow: you maintain graph **JSON/YAML** locally while the CLI uploads and syncs with Sudoiq, so you can treat “building agents” as its own repeatable dev flow.

When published, the platform assigns a stable identifier — the **`agent_id`** (UUID) you pass to **`run_agent`**, **`execute`**, or webhooks.

```mermaid theme={"theme":{"light":"github-light","dark":"github-dark"}}
flowchart LR
  author[Authoring] --> publish[Publish]
  publish --> agentId["agent_id in API"]
  agentId --> run[Start run]
```

Integrations only need the **`agent_id`** (and optional **version**) plus **inputs** (string slots, images, file references) to start execution.

## Related topics

* [How runs work](/concepts/how-runs-work)
* [Evals, tests, and feedback](/concepts/evals-tests-and-feedback)
* [Register server tools](/tools/register-server-tools)
* [Output validators](/validation/output-validators)
* [CLI](/clients/cli)