AI Agent

Introduction

The AI Agent Management Panel is the central place to create, configure, deploy, and manage AI agents in Autom Mate. Each agent is powered by a selected AI model and is automatically linked to an Autom, which defines the execution logic. After deployment, you can test your agent directly in the Playground before integrating it into a production workflow.

Agents Page

The Agents Page is the entry point for managing all of your AI agents.

• List View: Displays all existing agents, showing:

  • Agent Name

  • Model Type (GPT-4, GPT-4o, GPT-4-turbo, o3-mini, etc.)

  • Status (Active / Inactive)

  • Last Updated date

• Agent Actions:

  • Click on an agent to view and edit its configuration.

  • Delete an agent if it is no longer required (confirmation needed).

• Create Agent Button: Located in the top-right corner. This button launches the agent creation form.

Creating an Agent

When you click Create Agent, you are taken to Agent Details page. Here, you define how the agent will operate.

Configuration Fields

• Agent Name: A unique name that identifies the agent in the list.

• Selected Model: Choose the AI model (e.g., GPT-4, GPT-4o, GPT-4-turbo, o3-mini).

• Credentials: Authentication details required for model access.

• Temperature: Controls randomness in responses (lower = consistent, higher = creative).

• System Prompt: A structured instruction that defines the agent’s role, tone, and constraints.

Example Prompt

### Role - Primary Function
You are an AI assistant that helps users with inquiries, issues, and requests. 
Provide clear, friendly, and efficient responses.

### Constraints
1) Do not disclose internal data or training sources.  
2) Stay on topic; politely redirect off-topic questions.  
3) Answer only within provided context; otherwise, give a fallback response.  
4) Do not perform actions outside your defined role.  

Deployment

Click Deploy to activate the agent.

• This action automatically creates an Autom in the background.

• The Autom represents the agent’s workflow and can be accessed and modified later.

Managing the Autom

After deploying an agent, you will see the option Open Agent Autom.

Autom View

• Opens in a separate window.

• Shows the workflow (Autom) that powers your agent.

• Provides a visual way to extend or adjust the agent’s logic.

Editing the Autom

• You may add, modify, or remove steps.

• Every change directly impacts how the agent responds.

• Incorrect modifications may break triggers or response logic.

Trigger Method

• By default, the Trigger Method is API.

• This is how the Playground communicates with your agent.

• If you are not integrating with another chat interface, do not change this setting.

• If you do change it, Playground will no longer return responses.

Testing in Playground

The Playground is the built-in test console for AI agents.

Purpose

• Interact with your deployed agent in real time.

• Verify whether responses follow the system prompt and chosen model.

• Identify issues before moving to production.

How to Use

1. Open the Playground after deploying the agent.

2. Enter a message into the chat box.

3. Review the response generated by the agent.

4. Make adjustments in the agent configuration or Autom if needed, then retest.

What to Check

• Accuracy: Does the agent answer correctly?

• Consistency: Does it follow the system prompt across multiple queries?

• Latency: Are response times acceptable?

• Role Adherence: Does it stay within the defined behavior and constraints?

Data Sources – Managing Agent Knowledge Inputs

Purpose

The Data Sources tab defines how an AI Agent accesses and learns from information. This section allows users to add files, public websites, text entries, or integrated applications as data sources that form the agent’s knowledge base.

Accurate and relevant data sources directly enhance the agent’s response quality and contextual understanding.

Screen Overview

At the top of the page, the agent name and the “Last Updated” timestamp are displayed. Below that, the main navigation tabs appear:

Agent Details | Playground | Data Sources | Actions | Channels | Logs | Settings

The active tab is highlighted with a blue border — in this case, “Data Sources.”

The central content area presents four cards, each representing a type of knowledge input:

At the bottom, the “All added data sources” section lists every data item added. If no data has been added, an empty state icon appears with a short prompt message. A Filters button on the right lets users filter data by type or tags.

Upload Files

This option allows uploading files from the local system to enrich the agent’s knowledge.

Clicking the Upload Files card opens the Upload File modal window. In the center, a drag-and-drop area is displayed with the message:

“Upload File or Drag & Drop File here”

Supported file formats are listed below the box: pdf, doc, docx, txt, csv, pptx, json, md

Users can either choose a file manually using the “Choose File” button or drag and drop it directly. Once a file is selected, the Finish button becomes active.

Workflow

1. Click the Upload Files card.

2. Choose or drag-and-drop a file.

3. Click Finish.

4. The uploaded file appears in the “All added data sources” list below.

Each file automatically integrates into the AI Agent’s RAG (Retrieval-Augmented Generation) pipeline for contextual responses.

💡 Note: Unsupported file formats trigger a user-friendly error notification.

Public Websites

This feature allows the agent to learn from web-based content by adding website URLs.

Clicking the Public Websites card opens a modal titled Public Website. At the top, a URL input area labeled Crawl Website is displayed:

https:// [ Enter website URL ] [Load]

After entering a valid URL and clicking Load, the system scans the website. Detected links appear in a list below under:

“All Links (0/10 selected)”

Users can select up to 10 links to include as sources. Once selection is complete, the Finish button becomes active.

Workflow

1. Click Public Websites.

2. Enter the full URL of the site to be crawled.

3. Click Load to fetch the available pages.

4. Select the desired links (maximum of 10).

5. Click Finish to confirm.

💡 Tip: For large sites, limit your input to specific pages to avoid long crawl times and unnecessary data noise.

Text (Manual Entry)

This feature enables users to add textual information directly to train the AI Agent.

Selecting the Text card opens the Add Text window. It contains a simple, editor-style input area supporting basic formatting options:

• Bold (B)

• Italic (I)

• Lists (• / 1.)

• Links 🔗

• Emoji 😊

Up to 2000 characters can be entered. Once complete, the Finish button saves the entry.

Workflow

1. Click the Text card.

2. Type the desired content in the input area.

3. Use formatting tools if necessary.

4. Click Finish to save.

The entered text is then indexed into the agent’s vector knowledge base and becomes retrievable during query sessions.

💡 Note: Use this method for short, frequently updated or contextual information — not large documents.

Applications (Third-Party Sources)

This card is currently inactive (displayed in grey). It indicates a forthcoming feature where users will connect and pull data from external systems such as ServiceNow, Jira, or Confluence.

💡 Future Feature: Once active, this feature will allow agents to access enterprise systems directly, synchronizing structured knowledge into the Autom Mate AI ecosystem.

Data Management & Listing

Once added, each data source appears in the lower list labeled:

“All added data sources”

Each entry displays:

• Data type (File, Website, Text)

• Upload date

• Size or content summary

If no items exist, an empty-state icon with a neutral message is shown.

Actions – Defining and Managing Agent Capabilities

Purpose

The Actions section defines what the AI Agent can do — its functional capabilities. These are API-based or app-based operations that the agent can execute when responding to user queries, such as creating a Jira issue, sending a Slack message, or retrieving customer data.

Each action defines:

• The application or API the agent interacts with,

• The operation (e.g., “Create Issue”),

• The inputs required,

• The response structure returned to the user.

Screen Overview

At the top of the page, the same header and navigation layout appear:

Agent Details | Playground | Data Sources | Actions | Channels | Logs | Settings

When the Actions tab is selected, a blue underline highlights it.

The screen displays:

• A status indicator showing the number of actions created → 0/20 Actions

• A large Add Action button centered on the page.

If no actions exist, the message “No result found” is displayed in a neutral gray area.

Once actions are created, they appear in a list under Actions Added, each showing:

• Action name

• Creation date/time

• Status (e.g., Ready, Draft, or Error)

• Edit and Delete icons

Creating a New Action

To define a new action, click the + Add Action button. This opens the Add Action wizard — a step-by-step modal that guides users through creating an action.

Example Use Case

Scenario: A support team wants the AI Agent to create Jira tickets when users report issues in chat.

Steps:

1. Create an action → select Jira Service Management.

2. Choose Create Issue.

3. Connect a Jira credential.

4. Define inputs → summary, description, priority.

5. Describe usage: “When the user says they encountered a bug, create a Jira issue automatically.”

6. Save the action.

Now, when the agent detects a related query, it will call the Jira API and create the issue automatically.

Channels – Connecting the AI Agent to Communication Platforms

Purpose

The Channels tab allows your AI Agent to communicate with users across multiple platforms. Through this section, agents can be connected to WhatsApp, Microsoft Teams, Mate Chat, or via Webhook to external systems. Each channel represents a different communication entry point, ensuring that the agent can operate within the environment where users already work.

WhatsApp Integration

Connecting your AI Agent with WhatsApp Business enables automated conversations through WhatsApp chats. Once connected, messages received on the linked WhatsApp account are automatically processed by the agent in real time, allowing seamless customer or internal support interactions.

Setup Process:

1. Click Setup under the WhatsApp section.

2. Select an existing WhatsApp credential or create a new one.

3. After validation, the connection becomes active and the agent is reachable via the associated WhatsApp number.

💡 Tip: You must have a WhatsApp Business API or Meta-verified account already configured in Autom Mate before enabling this channel.

Microsoft Teams Integration

This integration enables the AI Agent to operate inside Microsoft Teams. Once connected, users can interact with the agent directly through Teams chats or channels — ideal for enterprise environments that already use Teams as their internal communication hub.

Setup Process:

1. Click Setup under Microsoft Teams.

2. Choose or add a valid Microsoft Teams bot credential.

3. Once authorization is completed, Autom Mate automatically links your AI Agent with that Teams bot.

4. All messages received by the bot are routed to the agent for processing and response.

💡 Tip: The bot must be registered in Azure Active Directory and configured as Multi-Tenant in the Azure portal to enable organization-wide or cross-tenant access.

Mate Chat (Autom Mate Native Channel)

The Mate Chat channel provides a native way to interact with your agent directly within the Autom Mate platform. This is useful for internal testing, demonstrations, or production-grade support scenarios without needing an external integration.

In the current release, this channel is not yet active — the setup option appears disabled. When available, it will provide a unified in-platform chat interface where users can test the agent’s responses instantly, similar to a live chatbot experience.

Webhook Integration

The Webhook channel enables programmatic integration between external systems and your AI Agent. Through this method, any external service can send data to the agent and receive structured responses in real time. It is particularly useful for automation workflows, ITSM tools, or alert-driven environments.

Setup Process:

1. Click Setup under Webhook.

2. The platform generates a unique endpoint URL for the selected agent.

3. Copy this URL and use it in external systems (e.g., ServiceNow, custom scripts, monitoring tools).

4. When data is sent to this endpoint, the AI Agent processes it and returns the defined structured output.

💡 Example Use Case: An alerting system can automatically trigger the agent when a critical event occurs. The agent can analyze the input, create a ticket via Actions, and respond with remediation steps — all through the Webhook connection.

Logs – Viewing AI Agent Conversations and Events

Purpose

The Logs tab allows users to review all conversation activities handled by the AI Agent. It helps track message exchanges, debug agent responses, and verify how the agent interacted with users through connected channels or the Playground.

Screen Overview

When the Logs tab is selected, the screen layout is divided into two main areas:

At the top-right corner, two action buttons are available:

• 🔄 Refresh: Reloads the latest conversation logs.

• ⬇ Export: Downloads the log data for offline review or audit purposes.

An additional quick-access button appears below the navigation bar: “Open in Autom Builder” – Opens the selected conversation directly inside Autom Builder for deeper analysis or workflow replay.

Empty State

If there are no logs yet, the screen shows an informational placeholder:

• Left Panel: “No logs found” Start a conversation to see logs here.

• Right Panel: “No messages in this thread.”

This state indicates that the agent has not yet processed any user interactions. Logs will automatically appear after the first message is received via Playground or a connected communication channel.

Using the Logs Screen

1. Interact with your AI Agent via Playground, WhatsApp, Microsoft Teams, or Webhook.

2. Each message exchange is automatically recorded and listed in the All Logs panel.

3. Select a conversation to view its message history in the right-hand panel.

4. Use Refresh to update the list in real time, or Export to download logs for review.