docs: document AI agents REST API access

guides/ai-agents/getting-started.mdx

@@ -235,3 +235,31 @@ Once a channel is designated as the multi-agent channel, all eligible agents in
 If you see the error **"This Slack channel is already assigned to another AI agent"** while trying to attach a second agent via the per-agent integration path, that path only supports single-agent channels. Switch to the org-level multi-agent channel setup described above instead.
 </Warning>
 
+## Manage AI agents via the API
+
+You can create, update, and interact with AI agents programmatically using the Lightdash REST API. This is useful when you want to provision agents from scripts, automate evaluations in CI, or build custom integrations on top of agent threads.
+
+The AI agent endpoints are documented in the [API reference](/api-reference/v1/introduction). They are all scoped to a project and live under:
+
+```
+/api/v1/projects/{projectUuid}/aiAgents
+```
+
+Common operations include:
+
+- Listing, creating, updating, and deleting agents
+- Configuring agent models, MCP servers, and verified content
+- Starting threads, sending messages, and streaming responses
+- Submitting feedback and managing artifacts produced by an agent
+
+Authenticate requests with a [personal access token](/references/workspace/personal-tokens):
+
+```bash
+curl -H "Authorization: ApiKey $LIGHTDASH_API_KEY" \
+  https://<your-lightdash-host>/api/v1/projects/<projectUuid>/aiAgents
+```
+
+<Note>
+AI agent endpoints require AI features to be enabled for your organization and that the calling user has access to the target project.
+</Note>
+