Agent mode features autonomous decision-making, environment awareness, and tool utilization capabilities. It can leverage project search, file editing, terminal access, and other tools to execute coding tasks efficiently. Additionally, you can configure Model Context Protocol (MCP) tools to further extend the AI coding assistant’s capabilities, making it even more aligned with development workflows. The main difference between Agent mode and Ask mode is that Agent mode can autonomously apply changes without requiring constant confirmation from you. Agent mode offers the following core features:
  • Project-level changes: Based on task description, Agent mode can autonomously break down tasks and modify multiple code files. Through multi-turn conversations, code optimization or snapshot rollbacks can be achieved to complete tasks more efficiently.
  • Plan making: Based on your inputs, Agent mode can create a step-by-step plan for you to review.
  • Automatic environment awareness: Agent mode automatically detects project frameworks, technology stacks, required code files, and error messages from task descriptions, eliminating the need to manually add project context.
  • Tool utilization: Agent mode autonomously uses various built-in tools, such as file read/write, code queries, and error troubleshooting. It also supports automatic discovery and use of MCP tools.
  • Command execution: Agent mode autonomously decides which commands to execute. It then generates these commands and runs them in the terminal.

​
Plan making by To-dos

  • Based on the inputs, Qoder will generate a plan to complete your requirements with a list of To-dos for you to review. If you would like to add more steps, just enter your requirements and Qoder will generate corresponding To-dos to the plan.
  • At the bottom of chats, you can view the progress of each tasks.
    • Empty circle - Task has not yet started.
    • Loading circle - Task is currently in progess.
    • Checkbox - Task is completed.

​
Programming tools

Qoder provides a wide range of programming tools for Agent mode to use autonomously. These tools support file searching, file reading, directory traversal, semantic symbol retrieval, file modification, error message retrieval, commands execution, and more. Agent mode can also plan its next steps based on the returned results.

​
Execute commands

Agent mode autonomously chooses and runs commands based on requirements. By default, you must confirm each command before it is executed.
  • If you click Run, Agent mode will send the command for execution.
  • If you click Cancel, Agent mode will skip running the command, and proceed to the next step based on your instructions.
For tasks running in the background, a “Running in Background” indicator will appear. Agent mode continues working on others tasks and returns to check the output when needed. You can set up an allowed list for automatic command execution in the Qoder Settings. Click the user icon or use the keyboard shortcut (⌘ ⇧ , （macOS）orCtrl shift ,(Windows)), select Qoder Settings, and navigate to Chat. To add multiple commands, separate them with commas.

​
MCP tools

If MCP tools are configured, Agent mode autonomously decides whether to call an MCP tool to complete tasks. It will ask for your confirmation before proceeding. Click Execute to confirm, and Agent mode will invoke the MCP tool. The results returned will then be used as context for the next steps. For more details on using MCP in Qoder, see MCP.