**Source URL:** https://limited.veevavault.dev/quality/ai-agents/api/retrieve-agent-action

# Retrieve Agent Action

<Aside type="note">
The functionality described on this page is only available to customers who have licensed Vault AI.
</Aside>

Retrieve the details of a specific agent action. This endpoint does not retrieve details for an agent action with *API Access* set to *false*.

<Endpoint path="/api/{version}/services/ai/agent_action/{agent_name}/{actionName}" method="GET" />

## Headers

<FieldTable>
| Name | Description |
| --- | --- |
| `Accept` | `application/json` (default) or `application/xml` |
</FieldTable>

## URI Path Parameters

<FieldTable>
| Name | Description |
| --- | --- |
| `{agent_name}` | The name of the agent to retrieve. For example, `promomats_document_chat__v`. |
| `{action_name}` | The name of the action to retrieve. For example, `spelling_grammar__v`. |
</FieldTable>

## Request

<CodeExample title="">
```bash
curl --location 'https://myvault.veevavault.com/api/v26.1/services/ai/agent_action/quick_check__v/spelling_grammar__v' \
--header 'Accept: application/json' \
--header 'Authorization: {AUTH_VALUE}' \
--header 'X-VaultAPI-ClientID: veeva-vault-api-reference-example'
```
</CodeExample>

## Response

<CodeExample title="">
```json
{
   "responseStatus": "SUCCESS",
   "agentAction": {
       "name": "spelling_grammar__v",
       "label": "Spelling and Grammar",
       "active": true,
       "source": "standard",
       "description": "Performs a mechanical proofreading check on the document. Identifies spelling errors, typos, malformed technical terminology, and structural grammatical faults (syntax, morphology, and punctuation). Focuses strictly on linguistic accuracy and reading flow, leveraging domain-specific medical knowledge to identify technical errors while ignoring regulatory or scientific validity.",
       "supportChat": false,
       "toolEvaluation": "AUTO"
   }
}
```
</CodeExample>

## Response Details

On `SUCCESS`, the response contains details about the specified agent and each action it can perform.

---

**Previous:** [Retrieve All Agent Actions](/quality/ai-agents/api/retrieve-agent-actions)  
**Next:** [Execute Agent Action](/quality/ai-agents/api/execute-agent-action)