# [4. Your First AI Agent](https://docs.getglow.ai/getting-started/tutorials/first-ai-agent#4-your-first-ai-agent)

> Deploy an interactive conversational assistant on the canvas with multi-turn session memory and a hosted public link.

Build a conversational assistant with **Chat Trigger** and an **AI Agent**. Set its instructions, pass conversation history into each turn, and test it on the canvas before sharing a hosted chat link.

**At a glance**

- **Use it to:** Build and test a two-Step conversational assistant (Hosted Chat Trigger + AI Agent) with session memory
- **Find it:** Automations → Create new → Workflow (Tools → Start → Chat Trigger + AI → AI Agent)
- **Cost:** Free for Chat Trigger · Glow AI tokens per agent turn (no external API key)
- **Limits:** Default caps: 10 iterations · 40 model calls · 25 tool calls · 180 active seconds
- **Output:** Interactive reply in the Chat tab and a Hosted Chat URL when Live
- **Instead:** AI Prompt (/build/ai-features/ai-prompt) for single-turn classification or drafting

You need Step credits and Glow AI tokens; the managed model needs no external API key. Keep the automation in **Draft** while testing. **Draft is not a sandbox:** each test message runs the agent for real and consumes tokens ([How testing works](https://docs.getglow.ai/build/the-canvas/testing-and-debugging#how-testing-works)).

[Chat Trigger](https://docs.getglow.ai/build/triggers/chat) → [AI Agent](https://docs.getglow.ai/build/ai-features/ai-agent)

[Open in Glow](https://app.getglow.ai) *(Creates a draft copy in your workspace; nothing runs automatically)*

> **What you will learn:** How **AI Agent** differs from **AI Prompt**, how
> **Chat Trigger** hosts a web chat page, how `historyText` compares with
> **Conversational Memory**, and how to test and share the live link.

---

## AI Prompt vs. AI Agent: The Difference

**AI Prompt** (Single Turn)

- Processes one input and returns one text or structured response.
- Does not call external tools or keep session memory.
- Best for classification, summarization, and one-shot drafting.

**AI Agent** (Multi-Turn & Tool Use)

- Built for interactive, multi-turn goals and conversation context.
- Calls permitted app tools and searches live web pages.
- Guided by instructions while tool permissions enforce boundaries.

---

## Step 1: Create a fresh automation

Open **Automations → Create new** (or **Create automation**) and select **Workflow**. Close the Workflow Assistant panel for extra canvas space.

---

## Step 2: Add the Chat Trigger

### Open the trigger catalogue

Click **Click to Add Trigger** on the canvas.

### Choose Chat Trigger

Select **Tools → Start → Chat Trigger** to open its App drawer.

### Configure the chat interface

| Field                              | Setting                               | Purpose                               |
| :--------------------------------- | :------------------------------------ | :------------------------------------ |
| **Mode**                           | `Hosted Chat`                         | Standalone public chat URL.           |
| **Authentication**                 | `None`                                | Admits anyone with the link.          |
| **Chat title**                     | `Glow Assistant`                      | Window heading.                       |
| **Welcome message**                | `Hi there! How can I help you today?` | Initial greeting.                     |
| **Input placeholder**              | `Ask me anything...`                  | Input box placeholder.                |
| **Conversation memory (messages)** | `20`                                  | Prior messages sent to `historyText`. |

---

## Step 3: Add the AI Agent

### Open the action placeholder

Click **Click to Add Action** next to the Chat Trigger.

### Choose AI Agent

Select **AI → Glow AI → AI Agent**.

### Select the Model

Keep **Brain (model)** set to **Gemini 4 Argon** (managed default).

### Set Primary Goals (Instructions)

Leave app tools off, keep the answer format as **Text**, and enter this prompt in **Instructions → Primary goals**:

```markdown
You are a friendly, helpful AI assistant.
Answer the user's questions clearly, accurately, and concisely.

Current user message:
{{ 1.chatInput }}

Recent conversation history:
{{ 1.historyText }}
```

`{{ 1.chatInput }}` passes the latest message and `{{ 1.historyText }}` passes prior messages from Step `1` (or pick them from **Workflow data**). Connect the Chat Trigger to the AI Agent; the final Step's text output becomes the chat reply.

Default **Advanced runtime limits** cap each run at **10 iterations**, **40 model calls**, **25 tool calls**, and **180 active seconds**. AI Agents run once per execution; use a [Repeater](https://docs.getglow.ai/build/action-steps/loops/repeater) to loop over a list.

---

## Step 4: Enable Conversation Memory

  

**Chat Trigger History**

    **Chat Trigger `historyText`** passes the last `20` messages into the
    prompt. It is sufficient on its own for this tutorial.
  

  

**Agent Conversational Memory**

    **Agent Conversational Memory** persists context across Agent runs keyed by
    `{{ 1.sessionId }}`.
  

### Turn on Memory

In the AI Agent's App drawer, open **Context** (or click **Memory** on the card) and turn on **Conversational Memory**.

### Select Conversation ID source

Set **Conversation ID source** to `Use data from an earlier Step`.

### Map the Session ID

In **Conversation ID**, select `sessionId` from Step 1 (`Chat Trigger`):

```text
{{ 1.sessionId }}
```

Each browser session keeps its own thread. For internal workspace-only chats, set **Authentication** on the Chat Trigger to **Glow User Auth**.

![Web Chat Trigger connected to an AI Agent on the canvas.](https://docs.getglow.ai/images/docs/ai/interactive-ai-agent-canvas.webp)
*Chat Trigger connects to the AI Agent. Keep the automation in Draft until chat tests pass.*

---

## Step 5: Test the Assistant on Canvas

Each test message runs the connected automation, consumes tokens, and executes any enabled tools even in Draft.

### Open the Chat tab

Select **Chat Trigger** and open the **Chat** tab in the App drawer.

### Send a fact to remember

Send this message and wait for the reply:

```text
Please remember my favorite fruit: Blueberry.
```

### Verify memory recall

Ask in the same chat:

```text
What is my favorite fruit that I just told you?
```

Confirm the agent replies `Blueberry`. To test Agent Memory alone, set **Conversation memory (messages)** to `0`, test a new fact, and restore it to `20`.

---

## Step 6: Go Live and Share

Check **Authentication** before publishing: **None** admits anyone with the link, while **Glow User Auth** requires workspace sign-in. Public chats spend workspace tokens and credits; per-visitor rate limits do not cap total spend.

1. Switch the top-left status from **Draft** to **Live**.
2. Select **Chat Trigger** and copy the **Hosted chat page** URL.
3. Open the URL in a new tab to chat with your live assistant.

---

## What you just built

- **Hosted chat UI:** Public or workspace-authenticated chat page.
- **Managed AI Agent:** Runs Gemini 4 Argon without an external API key.
- **Session memory:** Combines `historyText` with session-keyed Agent Memory (`{{ 1.sessionId }}`).

**Verify it works**

- **Run:** In the Chat Trigger Chat tab, send 'Please remember my favorite fruit: Blueberry.' then ask 'What is my favorite fruit that I just told you?'
- **You should see:** The AI Agent replies in the chat thread and recalls Blueberry.

## What's Next?

👉 **[Explore Use Cases & Examples →](https://docs.getglow.ai/getting-started/examples/overview)**

- **[Equip App Tools](https://docs.getglow.ai/build/ai-features/ai-agent#equip-tools)**: Toggle **Search the web** or attach app actions.
- **[Optional: Working Together](https://docs.getglow.ai/getting-started/tutorials/collaborating-on-a-canvas)**: Collaborate on a shared canvas.
- **[Chat Trigger Reference](https://docs.getglow.ai/build/triggers/chat)**: Configure Embedded Chat and auth.