Skip to content

3.1. Cowork Overview

Cowork transforms Backend.AI GO from a simple chatbot into an autonomous assistant capable of reasoning, using tools, and coordinating sub-agents to accomplish complex tasks.

What is Cowork?

Unlike a standard chat where the model just predicts the next text, Cowork follows a ReAct (Reasoning + Acting) pattern:

  1. Observe: Analyzes your request and the current environment.

  2. Think: Decides on a plan and determines if it needs a tool.

  3. Act: Executes a tool (e.g., searches the web, reads a file).

  4. Observe: Looks at the result of the tool and decides whether to continue or provide a final answer.

Key Benefits

  • Up-to-Date Information: Cowork can search the web to find information beyond the model's training data.

  • Practical Actions: Cowork can interact with your local files or run code to verify calculations.

  • Autonomous Reasoning: You give a high-level goal, and Cowork figures out the steps to get there.

  • Parallel Execution: Sub-agents can work on multiple tasks simultaneously for faster results.

When to Use Cowork

  • 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 Cowork

Cowork starting a task

  1. Click the Cowork icon in the sidebar.

  2. Select an Agent Profile (e.g., "General Assistant", "Web Researcher") from the profile selector.

  3. Choose a model that supports Tool Calling (look for the "Tool Calling" tag in your library).

  4. Enter your task in the task panel.

  5. Watch the agent's "Thought" process and tool execution in the timeline.

Cowork executing steps

Cowork progress Cowork progress

Cowork result Cowork result

Folder Permissions

Cowork requires explicit permission to access folders on your system. This ensures the agent only operates within directories you approve.

Permission Levels

Level Description
Read The agent can read files in the folder but cannot modify them.
Read & Write The agent can read and write files in the folder.
Full The agent has full access including creating, deleting, and moving files.

Managing Folder Access

  1. Open the Cowork panel from the sidebar.

  2. Click the Folders section to view permitted directories.

  3. Click Add Folder to open the folder picker and grant access to a new directory.

  4. Set the permission level for each folder.

  5. To revoke access, click the remove button next to a folder entry.

Principle of Least Privilege

Only grant the minimum permission level needed for your task. Use Read for research tasks and Read & Write or Full only when the agent needs to create or modify files.

Standing Instructions

Standing instructions are persistent directives that guide the agent's behavior across all tasks. They are injected into the system prompt for every interaction.

Global Instructions

Global standing instructions apply to all Cowork sessions regardless of which folder or profile is active.

  1. Open Cowork Settings from the sidebar.

  2. Navigate to the Standing Instructions section.

  3. Enter your global instructions (e.g., "Always respond in formal English", "Prefer Python over JavaScript for code tasks").

Folder-Specific Instructions

You can also set standing instructions that apply only when a specific folder is active:

  1. In the Folders section, click the settings icon next to a permitted folder.

  2. Enter folder-specific instructions (e.g., "This is a React project using TypeScript and Zustand", "Follow the coding conventions in CONTRIBUTING.md").

Folder-specific instructions are combined with global instructions and injected together into the system prompt.

Mid-Task Steering

While a Cowork task is running, you can provide real-time guidance to steer the agent's behavior without stopping and restarting the task.

How to Steer

  1. While a task is in progress, type your guidance in the steering input field below the task timeline.

  2. Press Enter to send the steering message.

  3. The agent will incorporate your guidance into its next reasoning step.

Steering messages can be up to 10,000 characters and are useful for:

  • Correcting the agent's approach ("Focus on the backend files, not the frontend")
  • Providing additional context ("The database uses PostgreSQL, not MySQL")
  • Adjusting priorities ("Skip the unit tests for now and focus on the main implementation")

Sub-Agent Coordination

For complex tasks, Cowork can spawn sub-agents that work in parallel on different parts of a task.

How Sub-Agents Work

  • The main agent analyzes your task and breaks it into sub-tasks when beneficial.
  • Each sub-agent runs independently with its own tool access and reasoning chain.
  • Results from sub-agents are collected and synthesized by the main agent.

Configuring Sub-Agents

  • Max Concurrent: Set the maximum number of sub-agents that can run simultaneously in Cowork Settings. Higher values allow more parallelism but consume more resources.

Sub-Agent Tracker

The Cowork UI includes a tracker that shows:

  • Active sub-agents and their current status
  • What each sub-agent is working on
  • Progress of individual sub-tasks
  • Results as they complete

Understanding the Status Indicator

The Cowork interface displays a prominent status badge that shows the current state:

Status Color Description
Ready Green Cowork 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 Cowork, use models specifically trained for tool calling, such as Qwen3 variants.