Agent Mode Overview¶
Agent Mode transforms Backend.AI GO from a simple chatbot into an autonomous assistant capable of reasoning and using tools to accomplish complex tasks.
What is an AI Agent?¶
Unlike a standard chat where the model just predicts the next text, an Agent follows a ReAct (Reasoning + Acting) pattern:
-
Observe: Analyzes your request and the current environment.
-
Think: Decides on a plan and determines if it needs a tool.
-
Act: Executes a tool (e.g., searches the web, reads a file).
-
Observe: Looks at the result of the tool and decides whether to continue or provide a final answer.
Key Benefits¶
-
Up-to-Date Information: Agents can search the web to find information beyond their training data.
-
Practical Actions: Agents can interact with your local files or run code to verify calculations.
-
Autonomous Reasoning: You give a high-level goal, and the agent figures out the steps to get there.
When to Use Agent Mode¶
-
Researching: "Find the latest pricing for NVIDIA RTX 50 series GPUs."
-
Data Analysis: "Read the CSV file in my Documents folder and summarize the sales trends."
-
Code Debugging: "Run this Python script and tell me why it's throwing a SyntaxError."
Getting Started with Agents¶

-
Click the Agent icon in the sidebar.
-
Select an Agent Template (e.g., "General Assistant", "Web Researcher").
-
Choose a model that supports Tool Calling (look for the "Tool Calling" tag in your library).
-
Enter your task in the chat box.
-
Watch the agent's "Thought" process and tool execution in the timeline.



Understanding the Status Indicator¶
The agent interface displays a prominent status badge that shows the current state of your agent:
| Status | Color | Description |
|---|---|---|
| Ready | Green | The agent is ready to accept a new task. A gentle pulse animation indicates availability. |
| Thinking | Amber | The agent is actively processing your request. The pulse animation indicates ongoing work. |
| Paused | Amber | The agent has been temporarily paused. You can resume or stop the task. |
| Waiting for Approval | Amber | The agent needs your approval before executing a high-risk tool (e.g., writing files). |
| Completed | Green | The task has finished successfully. |
| Stopped | Gray | The task was manually stopped before completion. |
| Error | Red | An error occurred. Check the error message for details and suggested actions. |
Progress Tracking¶
Below the status badge, a visual progress bar shows:
- Completed steps: Filled portion of the bar
- Current step description: What the agent is currently doing
- Step count: "Step X of Y" format
Model Choice Matters
For best results in Agent Mode, use models specifically trained for tool calling, such as Qwen3 variants.