# Building Apps with AI Agents

Here’s a **basic description** you can use in a Knowledge Base, onboarding doc, or sales collateral that outlines the **four primary deployment types for AI Agents in raia**:

***

## **Deployment Types of AI Agents in raia**

The **raia platform** supports multiple AI Agent deployment types depending on your business goal — whether you're answering questions, qualifying leads, automating actions, or handling conversations across multiple channels.

Here are the four main ways to deploy AI Agents:

***

### **1.** [**Conversational AI Agents**](#id-1.-conversational-ai-agents)

**Purpose:** General-purpose, multi-channel agents that respond to user questions via **Live Chat, SMS, Email, or Voice**. 

\
**Use Cases:** Assistants.

\
**Deployment:**

* Built in **Launch Pad**
* Trained on documents, Packs, or instructions
* Tested in **Copilot**

***

### **2.** [**Support AI Agents (Knowledge Base Driven)**](/dev-program/agents/building-an-support-ai-agent.md)

**Purpose:** Internal or external-facing agents trained specifically on company documentation to answer policy, process, or technical questions.

\
**Use Cases:**

* Internal IT/support team help
* Employee self-service tools
* Customer-facing knowledge base automation

\
**Key Features:**

* Integrated with **raia Connect** for AI-ready document ingestion
* Deployed through **Copilot** (internal) or **Live Chat** (external)
* Supports scoring, escalation, and ticketing integrations

***

### **3.** [**Sales AI Agents (Conversion Driven)**](/dev-program/agents/building-a-sales-ai-agent.md)

**Purpose:** Engage prospects, ask qualifying questions, provide product information, and escalate hot leads to human sales reps.

\
**Use Cases:**

* SDR follow-up
* Website chat-to-lead conversion
* Lead re-engagement via SMS/email

\
**Key Features:**

* Can run via **outbound campaigns** or **triggered from CRM**
* Uses **Scoring Skill** to assess lead quality
* Alerts reps via **Notification Skill**
* Logs conversations via **Webhook Skill**

***

### **4. Autonomous AI Agents (Workflow Embedded)**

**Purpose:** Agents embedded inside automated workflows to complete background tasks without human input.

\
**Use Cases:**

* Auto-tagging support conversations
* Summarizing and scoring chats
* Processing incoming form data
* Triggering downstream actions via webhooks

\
**Deployment:**

* Can be triggered via **functions**, **webhooks**, or internal **workflow orchestration**
* Often used for **backend automation**, not end-user interaction
* Supports **function chaining**, document processing, and API calls


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.raiaai.com/dev-program/agents/building-apps-with-ai-agents.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.