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

# AI Module (Ami)

> AI assistant, domain agents, automations, prompts, and usage tracking.

### Overview

AI (branded "Ami" in-product) is AmDital's cross-module AI surface: a general assistant, five
domain-specific agents, a visual automation builder, a prompt library, run history, and usage/cost
tracking. Because agents and automations act across modules, this is the one module with no single
dependency — it can read and act on data from any other module you've enabled, plus
[Integrations](/docs/modules/integrations) for webhook and MCP connections.

### Where to find it

| Area | Route |
| - | - |
| AI Assistant | `/ai` |
| Domain agents (Sales, HR, Finance, Support, Dev) | `/ai/agents/sales`, `/ai/agents/hr`, `/ai/agents/finance`, `/ai/agents/support`, `/ai/agents/dev` — also reachable via the top-level `/agents` alias |
| Agent playground | `/ai/agents/playground` |
| Automations (builder, triggers, templates, webhooks) | `/ai/automations`, `/ai/automations/builder`, `/ai/automations/triggers`, `/ai/automations/templates`, `/ai/automations/webhooks` — also reachable via `/automation` |
| Paused / failed automation runs | `/ai/automations?status=paused`, `/ai/automations?status=failed` |
| Memory / prompt library / run history | `/ai/memory`, `/ai/prompts`, `/ai/prompts/test`, `/ai/history` |
| Usage / cost tracking | `/ai/usage`, `/ai/costs` |
| AI configuration (provider/keys) | `/settings/ai-configuration` |

### Core workflows

#### Chat with the assistant or a domain agent

1. Open **AI** for the general assistant, or pick a domain agent (**Sales**, **HR**, **Finance**,
   **Support**, **Dev**) for one scoped to that module's data and actions.
2. **Memory** stores facts the assistant should remember across conversations (e.g. your name or a
   standing preference) — add or edit entries directly.
3. Every conversation is recorded in **History**, searchable later.

#### Build an automation

1. Go to **Automations → Builder** to define a trigger and the steps that run when it fires, or
   start from a **Template**.
2. **Triggers** lists the trigger rules across all your automations; **Webhooks** manages
   automations kicked off by an inbound webhook rather than an in-app event.
3. A failed or paused run shows up filtered at `/ai/automations?status=failed` or `?status=paused`
   for triage.

#### Manage prompts

* **Prompt Library** stores reusable prompts; **Test** a prompt before saving it into the library.

#### Track usage and cost

* **Usage** and **Costs** report AI call volume and spend, useful for keeping an eye on a
  workspace's AI budget.

### Permissions

Workspace-scoped. Individual domain agents are expected to respect their parent module's own
permission gates (e.g. the Finance agent shouldn't surface data a viewer couldn't see in Finance
directly) — this is not yet broken out into a separate, explicit permission matrix per agent.

### Known limitations

* Per-agent permission gating (beyond the general workspace-scoped access) is not yet a distinct,
  documented matrix — don't assume a domain agent enforces the exact same field-level restrictions
  as its parent module without checking directly.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.