AI Chat with the awork Agent
Chat with the awork Agent to find projects and tasks, create content, search the web, and generate images using natural language prompts
The awork Agent knows your awork context and can not only answer questions, but also look things up in awork and perform actions there.
Main Benefits and Use Cases
The awork Agent is the built-in agent. You can get started right away without setting up an agent yourself.
It helps you with things like:
-
Finding information – Discover projects, tasks, or other information in awork
-
Getting tasks done – Let tasks be created or modify existing content
-
Using the web and images – The agent can use web search and image generation
-
Working with your awork context – Link projects, documents, and files directly to a thread
-
Switching to voice input – Dictate your input using the microphone instead of typing
Typical questions might be about current project status, available capacity, or assigning a task to a customer.
How to Open the Chat Interface
You can access the awork Agent in 2 ways:
- Click on AI in the main menu
- Or click the awork AI chat button in the floating action bar at the bottom of the screen (recognizable by the robot icon)
Both views use the same thread history.
The input field for your prompt will open.
Show Threads
Click the Threads icon in the panel header to open an overview of your previous conversations. Threads are grouped by categories like "Awaiting Action" and "Recently Used".
Customize View
Various view options are available in the chat window header:
- Show as Sidebar: Docks the panel as a sidebar on the right edge
-
Show as Popup: Displays the panel as a floating window
-
Expand Size: Enlarges the panel
-
Make Smaller: Reduces the panel size
-
Dock and Undock Sidebar
When the panel is displayed as a sidebar, you can use Dock AI Chat Sidebar to lock the sidebar in place, or Undock AI Chat Sidebar to release it again.
- Close Chat Panel
Click the X icon in the top right corner of the panel header to close the chat window. Alternatively, you can use the Esc key.
Managing Threads
A conversation with an agent is called a Thread.
Your threads are saved so you can come back to them later.
In the thread list, you can:
-
Create threads
-
Search for threads
-
Pin threads
-
Open and reuse threads
Using the action button for a thread, you have these options:
-
Rename
-
Add to Project
-
Copy ID
-
Copy Link
-
Archive
-
Delete
A thread contains more than just its messages. This includes files generated by the agent as well as tools and connectors that were used.
Selecting and Using an Agent
Every new thread starts with the awork Agent by default.
You can instead select a custom agent when creating a new thread:
-
Open a new thread
-
Select a custom agent from the agent selection field
-
Start the thread
The selection shows available custom agents alphabetically. There is no list for recently used or favorite agents.
After the first message, the agent for this thread is set. You cannot switch agents within a thread. To use a different agent, you need to start a new thread.
Custom agent threads show the agent's avatar in the thread list. Threads with the awork Agent do not show an agent avatar there.
Working with Context from awork
The awork Agent can work with your existing awork context.
-
Use the @ mention to reference awork objects and include projects, documents, or files in a thread.
-
Or click the Plus icon in the bottom left of the input field. A menu labeled "Context & Abilities" will appear with various options for adding content.
-
Upload File: Add files as context. Alternatively, you can insert files via drag and drop or copy and paste.
-
Add Context: Provide additional context.
Choose Person, Team, Customer, Task, Project, Doc, or Current Page Context.
-
For best results, you should provide relevant context directly. This way the agent has to infer or guess less from your workspace.
A direct context reference is often more reliable than just writing an object's name as regular text in your prompt.
Adding Abilities
Select Skills
Click the Plus icon in the bottom left of the input field. In the menu that opens, you'll find these options:
- Skills: Enable abilities for the agent. In the panel that appears, you can activate additional skills via "Manage in Library".
- Connectors (MCP): Set up external connections. Available connectors like Notion are shown in the side panel, where you can enable or disable them using toggle switches.
- Tools: Activate tools like web search and awork access
- Activate Tools: Click on Tools to turn on or off tools like Web Search and awork Access. Both options can be controlled with switches.
Controlling the awork Agent's Thinking Mode
Choose Performance Mode
You can select how fast or thorough you want the awork Agent to work. Click the Balanced button below the input field.
Three simple presets are available for this:
-
Fast – For quick answers
-
Balanced – Balanced performance (default setting)
-
Deep thinking – For more complex tasks requiring more thinking time
You can select the underlying model and reasoning level yourself through advanced mode.
The reasoning level determines how much effort the model puts in before answering. A higher level can deliver better results for difficult tasks, but works more slowly.
Not every model supports every reasoning level.
Workspace administrators can determine which model and reasoning level are used behind the three presets.
Enable Advanced Settings
In the performance menu below the modes, you'll find the Advanced option with a toggle switch. Enable this option to display additional settings like Reasoning Level, Image Model, and a choice of different AI models.
In advanced mode, each model also displays the region in which it is deployed. This refers to the deployment region of the model, not the provider's country of origin.
This selection can be restricted by a regional list set by the workspace administrator.
Switching Models During a Thread
You can also switch the model after starting a thread.
Keep in mind that the conversation context so far is cached with the provider. This way it doesn't have to be fully reprocessed with each follow-up message.
This cache is tied to a specific model. When you switch models, the next run cannot use the previous cache and will be charged at the full, higher rate for non-cached context.
Sending Messages While Processing
You don't have to wait for the agent to finish answering.
If you send another message while a run is in progress, it will be queued. Up to 10 messages can be processed one after another per thread.
Processing follows the order in which you sent the messages by default.
You can also prioritize a message that is already waiting. This ends the current run and starts the selected message instead.
Using Voice Input
There's a microphone icon in the input field. You can use it to dictate your input. Your spoken prompt will be converted to text and sent as a regular message to the agent.
Note: This is a dictation feature, not a spoken conversation with the awork Agent.
Performing Actions with the awork Agent
The awork Agent can not only read awork data, but also edit it.
This includes, for example, creating or modifying tasks and documents.
Before the agent creates, edits, or deletes anything in awork, it asks for your confirmation.
The awork Agent does not make changes quietly in the background. Write actions in awork require your confirmation beforehand.
Memory and Workspace Context
The awork Agent can store information about you, a customer, or a project.
Different rules apply here:
-
Personal Information applies to you personally
-
Project-related Information is used when the agent works in this project context
-
Customer-related Information is used when the agent works in the corresponding customer context
This memory runs in the background. There is no view where you can see or manage stored memories.
Additionally, there is the Workspace Context. A team can store shared background knowledge there, such as company knowledge, terms, rules, and working methods.
All workspace members can read the workspace context. Only users with the appropriate workspace configuration permissions can edit it.
The workspace context does not give agents additional tools or permissions.
FAQ
Is the awork Agent a custom agent?
No. The awork Agent is the built-in agent for all users. Custom agents, on the other hand, are saved agents that can be set up and shared for specific recurring tasks.
Can I switch agents within a thread?
No. Once the first message is sent, the agent for that thread is set. To use a different agent, you need to start a new thread.
Can the awork Agent make changes in awork?
Yes. For example, it can create or edit tasks and documents. Before write actions in awork, it asks for your confirmation.
Can the awork Agent use other tools?
Yes. It can search and edit awork data, use web search, generate images, and access other tools through connected apps.
Can I understand what the agent did?
Yes. Agent actions are recorded in awork's activity logs with the responsible user and the agent used, making them fully traceable.
