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

# Modes

> Built-in modes for common tasks and custom modes with your own instructions, tools, and permissions.

A mode defines what the agent focuses on: its instructions, model, capabilities, and where it can be invoked (dashboard, API, Slack).

## Built-in modes

| Mode                    | Use it for                                                     |
| ----------------------- | -------------------------------------------------------------- |
| `auto`                  | General Kapso Agent assistance - the default                   |
| `api`                   | Inspecting and debugging project APIs and WhatsApp behavior    |
| `workflows`             | Building, inspecting, and debugging workflows                  |
| `inbox`                 | Operating live inbox conversations                             |
| `findings`              | Reviewing recurring problems and their evidence                |
| `findings-investigator` | Background investigation of findings                           |
| `meta-onboarding`       | Setting up and recovering WhatsApp Business connections        |
| `meta-business-agent`   | Configuring and testing Meta Business Agent connectors         |
| `whatsapp-templates`    | Creating, managing, and troubleshooting WhatsApp templates     |
| `whatsapp-flow`         | Building and debugging WhatsApp Flows and their data endpoints |

The [Agent API](/docs/kapso-agent/api) can trigger `auto`, `api`, `workflows`, `findings`, `findings-investigator`, `meta-onboarding`, `whatsapp-templates`, and `whatsapp-flow`. `inbox` and `meta-business-agent` are dashboard-only. Check `available_invocations` in the modes list for the current set. Custom modes need the `api` surface. `findings-investigator` runs in the background with auto-approval and does not appear in the mode picker.

## Custom modes

Create your own modes under **Kapso Agent → Modes**. Project owners and admins can create and edit them. A mode requires a name, instructions, and a model.

Configurable per mode:

* **Instructions** - the mode's system prompt.
* **Model and reasoning effort** - fixed for every run in this mode.
* **Surfaces** - where the mode can be invoked: `ui`, `api`, `slack`. At least one is required.
* **Capabilities** - what the agent is allowed to do (see below).
* **Resources** - MCP connections, GitHub repositories, and encrypted environment variables. See [Resources](/docs/kapso-agent/resources).
* **Sandbox** - read-only or command execution, with approval, network, secret, and setup controls. See [Sandbox](/docs/kapso-agent/resources#sandbox).

The mode's slug is generated on creation and can't be changed afterwards.

## Capabilities

| Capability                   | What it allows                                          | Approval                                      |
| ---------------------------- | ------------------------------------------------------- | --------------------------------------------- |
| `read_messages`              | Read WhatsApp conversations and their messages          | -                                             |
| `read_findings`              | Read findings and their evidence                        | -                                             |
| `send_messages`              | Send WhatsApp messages                                  | Always required                               |
| `modify_workflows`           | Create, edit, and debug workflows                       | Configurable                                  |
| `operate_workflows`          | Inspect workflow executions, and start and resume them  | Starting and resuming always require approval |
| `read_agent_sessions`        | List Kapso Agent sessions and read their history        | -                                             |
| `collaborate_agent_sessions` | Start sessions in other modes and send messages to them | Configurable                                  |
| `read_project_files`         | Read files from repositories assigned to the mode       | -                                             |
| `run_sandbox_commands`       | Run commands and edit files in the mode's sandbox       | Configurable                                  |
| `search_logs`                | Search project logs                                     | -                                             |

New custom modes start with `read_messages` and `read_findings`. `read_project_files` can't be toggled - it's granted when you assign a repository to the mode.