> ## Documentation Index
> Fetch the complete documentation index at: https://outlit-codex-platform-actions-create-update-cli.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Platform Actions

> Inspect and configure Outlit agents and automations through API, CLI, and MCP

Platform actions expose selected Outlit platform configuration through the same API, CLI, and MCP surfaces that agents already use for customer context. They are meant for workflows where an agent needs to inspect or safely prepare configuration without clicking through the Outlit UI.

Use platform actions for Outlit-hosted agents, automations, signals, and destinations. Use [Integration Routes](/api-reference/integrations) for connecting external data sources such as Slack, Stripe, HubSpot, PostHog, or support tools.

## How the Surfaces Fit Together

| Surface  | Use it when                                                                                | Entry point                                                          |
| -------- | ------------------------------------------------------------------------------------------ | -------------------------------------------------------------------- |
| REST API | You are building your own app, backend job, or schema-driven integration                   | [OpenAPI spec](/openapi.json)                                        |
| CLI      | You want a human or coding agent to run commands from a terminal                           | [CLI commands](/cli/commands#agents)                                 |
| MCP      | You want an MCP client to inspect or prepare platform configuration while assisting a user | [MCP Integration](/ai-integrations/mcp#platform-configuration-tools) |

Each surface calls the same platform action contracts. The transport changes, but the intent does not: the API exposes the canonical route, the CLI wraps that route for terminal use, and MCP exposes the same operation as an agent tool.

## Naming Model

Platform actions use resource-first names so humans and agents can predict what to call next:

| Surface  | Pattern                        | Example                                          |
| -------- | ------------------------------ | ------------------------------------------------ |
| CLI      | `outlit <resource> <verb>`     | `outlit agents update <id> --instructions "..."` |
| REST API | Standard resource routes       | `PATCH /api/agents/{id}`                         |
| MCP      | `<resource>_<verb>` tool names | `outlit_agent_update`                            |

Subtypes and templates are inputs, not command names. For example, use `outlit agents create --template churn` to create a template-backed agent, and use `outlit destinations create --type webhook` to create a webhook destination.

Agent and destination updates patch only the fields provided. Automation and signal updates currently take full configuration bodies, so agents should read the current resource first, preserve fields they do not intend to change, and then send the updated body.

## Current Scope

The current platform action set focuses on the Agents and Automations areas of the Outlit platform.

| Area         | Read actions                                                                | Write actions                            |
| ------------ | --------------------------------------------------------------------------- | ---------------------------------------- |
| Agents       | List templates, list available actions, list agents, get one agent          | Create, update, enable, disable, rename  |
| Automations  | List automations, get one automation                                        | Create, update, enable, disable, archive |
| Signals      | List configured automation signals, get one signal                          | Create, update, archive                  |
| Destinations | List configured destinations, get one destination with masked configuration | Create, update, enable, disable, archive |

For example, a CLI user or agent can create a draft template and then explicitly enable or disable lifecycle resources:

```bash theme={null}
outlit agents create --template churn --json
outlit agents create --type custom --display-name "Renewal risk" --instructions "Find risk" --surface-criteria "Surface risky customers" --json
outlit signals create --file ./signal.json --json
outlit automations create --file ./automation.json --json
outlit agents enable 10000000-0000-4000-8000-000000000004 --json
outlit automations disable 10000000-0000-4000-8000-000000000001 --json
```

Template creation creates supported template resources in `draft` mode. Draft creation does not enable an automation, add schedules, add external destinations, or send notifications by itself. Lifecycle write actions mutate only the named resource state.

Automation create and update actions are agent-centered. Callers provide `agentId`; update bodies also provide `name`, `enabled`, and `triggerType` explicitly. Outlit maps the agent ID to the hosted-agent processor internally and does not require callers to construct raw processor JSON.

## Safety Model

Platform actions are designed to make configuration inspectable before they make it broadly mutable.

* Read actions require an API key with the `agents:read` scope.
* Write actions require an API key with the `agents:write` scope.
* Template creation returns explicit safety metadata describing what was created and what was not enabled.
* Enable actions validate the current platform state before enabling. For example, an automation cannot be enabled if required destinations or processor agents are unavailable.
* Destination responses only include masked configuration through fields such as `maskedConfig`; raw secrets and unmasked provider configuration are not returned.
* Responses are projected platform-action DTOs, not raw database rows.
* Error responses use command envelopes with stable error codes such as `authorization_denied`, `validation_failed`, `not_found`, and `conflict`.

## Response Shape

Platform actions return command envelopes. Successful responses include a `commandId`, `commandVersion`, `correlationId`, and `result`. The useful payload is under `result.data`.

For example, `outlit automations list --json` returns automation data under:

```text theme={null}
result.data.automations
```

Errors return `ok: false` with an `error` object and correlation ID so agents can report the failure precisely or retry only when the error is retryable.

## Example Agent Workflow

A coding agent or MCP client can use platform actions to inspect what exists, choose a safe action, and leave the user with reviewable platform state:

```bash theme={null}
outlit agents templates --json
outlit agents actions --json
outlit agents create --template churn --json
outlit agents update 10000000-0000-4000-8000-000000000004 --instructions "Prioritize recent support escalations" --json
outlit destinations create --type webhook --name "Customer ops" --url https://hooks.example.com/outlit --json
outlit destinations update 10000000-0000-4000-8000-000000000003 --type webhook --name "Customer ops" --json
outlit agents enable 10000000-0000-4000-8000-000000000004 --json
outlit agents list --json
outlit automations list --json
outlit automations enable 10000000-0000-4000-8000-000000000001 --json
outlit signals list --json
outlit destinations list --json
```

This workflow lets the agent discover available templates, understand supported action capabilities, create a draft churn agent template, inspect the resulting agent and automation configuration, and then make explicit lifecycle changes.

## Available REST Routes

| Route                                 | Purpose                                                             |
| ------------------------------------- | ------------------------------------------------------------------- |
| `GET /api/agent-templates`            | List supported agent templates                                      |
| `GET /api/agent-actions`              | List available agent configuration actions                          |
| `GET /api/agents`                     | List configured agents                                              |
| `GET /api/agents/{id}`                | Get one configured agent                                            |
| `POST /api/agents`                    | Create an agent                                                     |
| `PATCH /api/agents/{id}`              | Update one configured agent                                         |
| `POST /api/agents/{id}/enable`        | Enable one configured agent                                         |
| `POST /api/agents/{id}/disable`       | Disable one configured agent                                        |
| `POST /api/agents/{id}/rename`        | Rename one configured agent                                         |
| `GET /api/automations`                | List configured automations                                         |
| `POST /api/automations`               | Create an agent automation                                          |
| `GET /api/automations/{id}`           | Get one configured automation                                       |
| `PATCH /api/automations/{id}`         | Update one agent automation                                         |
| `POST /api/automations/{id}/enable`   | Enable one configured automation                                    |
| `POST /api/automations/{id}/disable`  | Disable one configured automation                                   |
| `POST /api/automations/{id}/archive`  | Archive one configured automation                                   |
| `GET /api/signals`                    | List configured automation signals                                  |
| `POST /api/signals`                   | Create one automation signal                                        |
| `GET /api/signals/{id}`               | Get one configured automation signal                                |
| `PATCH /api/signals/{id}`             | Update one automation signal                                        |
| `POST /api/signals/{id}/archive`      | Archive one configured automation signal                            |
| `GET /api/destinations`               | List configured automation destinations with masked configuration   |
| `GET /api/destinations/{id}`          | Get one configured automation destination with masked configuration |
| `POST /api/destinations`              | Create one automation destination                                   |
| `PATCH /api/destinations/{id}`        | Update one automation destination                                   |
| `POST /api/destinations/{id}/enable`  | Enable one configured automation destination                        |
| `POST /api/destinations/{id}/disable` | Disable one configured automation destination                       |
| `POST /api/destinations/{id}/archive` | Archive one configured automation destination                       |

The [OpenAPI spec](/openapi.json) is the canonical reference for request and response schemas.
