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

# ResponseCX API

> The API behind AI agents that resolve customer work — resources, auth, and where to start.

# ResponseCX API

ResponseCX agents resolve customer work end to end: they look up the order, apply your policy, take
the action, and close the ticket. This is the API that configures and observes them.

Agents are **not chatbots**. A chatbot returns text; a ResponseCX agent issues the refund. That
difference is why the resources below are mostly about *constraints* — what an agent may do, and
when it must defer.

## Base URL and auth

```
https://api.stateset.com/v1
```

```bash theme={null}
curl https://api.stateset.com/v1/agents \
  -H "Authorization: Bearer $STATESET_API_KEY"
```

| Key prefix | For                 |
| ---------- | ------------------- |
| `sk_test_` | Sandbox development |
| `sk_live_` | Production          |

Create keys in **Dashboard → Settings → API Keys**. They're shown once.

## The resources

**Configuring behaviour** — start here, because these decide what the agent is allowed to do:

| Resource                                                                                                                      | Purpose                                       |
| ----------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------- |
| [Agents](/response-api-reference/agents/list)                                                                                 | The agents themselves                         |
| [Settings](/response-api-reference/settings)                                                                                  | Model, skip rules, escalation, human takeover |
| [Rules](/response-api-reference/rules)                                                                                        | Named policy constraints                      |
| [Functions](/response-api-reference/functions/list) · [Function Parameters](/response-api-reference/function-parameters/list) | Tools an agent can call                       |
| [Attributes](/response-api-reference/attributes/list)                                                                         | Agent behaviour and knowledge settings        |

**Conversation:**

| Resource                                                   | Purpose                   |
| ---------------------------------------------------------- | ------------------------- |
| [Messages](/response-api-reference/messages)               | Individual turns          |
| [Channel Threads](/response-api-reference/channel-threads) | Threads grouping messages |
| [Sessions](/response-api-reference/sessions/list)          | Conversation sessions     |
| [Responses](/response-api-reference/responses/get)         | What an agent produced    |

**Knowledge and memory:**

| Resource                                              | Purpose                              |
| ----------------------------------------------------- | ------------------------------------ |
| [Embeddings](/response-api-reference/embeddings/list) | Vector representations for retrieval |
| [Memories](/response-api-reference/memories/list)     | Persistent per-customer context      |
| [Examples](/response-api-reference/examples/list)     | Past interactions used as templates  |

**Operations:**

| Resource                                            | Purpose                 |
| --------------------------------------------------- | ----------------------- |
| [Schedules](/response-api-reference/schedules/list) | Scheduled agent work    |
| [Users](/response-api-reference/users)              | Operators and customers |

## Where to start

<CardGroup cols={2}>
  <Card title="Set up ResponseCX" icon="rocket" href="/stateset-response/stateset-responsecx">
    Connect integrations, configure an agent, first workflow.
  </Card>

  <Card title="Settings reference" icon="sliders" href="/response-api-reference/settings">
    The 22 fields that decide agent behaviour.
  </Card>

  <Card title="Public API (v1)" icon="code" href="/stateset-response/response-public-api">
    Build and tune agents programmatically.
  </Card>

  <Card title="MCP servers" icon="plug" href="/stateset-response/response-mcp">
    Drive agent-building from Claude.
  </Card>
</CardGroup>

## What sits underneath

The API is the surface. The parts that make an agent trustworthy live below it:

| Layer                                                            | What it contributes                                         |
| ---------------------------------------------------------------- | ----------------------------------------------------------- |
| [Workflow Studio](/stateset-response/responsecx-workflow-studio) | A 15-phase pipeline per brand, with a review gate           |
| [Temporal engine](/next-temporal/overview)                       | Durable, replayable execution — an escalation can wait days |
| [Decision gate](/next-temporal/policy-engine)                    | Per-action authorisation with cited proofs                  |
| [Sync](/stateset-sync-server-api-basics)                         | 186 integrations the agent can reach                        |

Generative and deterministic operations are blended deliberately: the model reads the messy request,
and deterministic workflows execute the consequential parts. Every action is traceable.

## Related

* [ResponseCX Platform](/stateset-response/responsecx-platform) — architecture and the outcome model
* [Workflows](/stateset-response/stateset-responsecx-workflows) — what teams automate first
* [Authentication](/response-api-reference/authentication)