Agent Memory and Context Window
Understand how the awork Agent uses conversation context and personal memories within threads and across chats to deliver better results with focused tasks.
Memory stores selected information across threads; the context window limits how much information can be considered within a thread.
The awork Agent uses conversation context and personal memories. Find out what carries over between chats and how to get better results.
What the awork Agent remembers
Within a thread, the Agent takes into account the conversation so far, any existing artifacts, meaning files and results provided or created in the thread, and the related context. After context compression, only a shortened summary of this information may be available.
Across different chats, awork currently supports personal memories for the awork Agent. These can be permanent preferences or facts, saved automatically or at your explicit request.
Personal memories are private and tied to your user account.
What the Agent doesn't remember across threads
Not everything from a chat automatically becomes the Agent's long-term knowledge.
-
No automatic learning from chats: Neither the Agent nor the model learns from your chats.
-
Custom Agents don't currently have a memory feature: They don't automatically carry this information over to new threads.
-
Separate memories in shared threads: In a shared thread, each user's memories are applied to their own messages.
Custom specialized Agents don't have a memory feature yet. However, you can adjust their prompt for future threads by explicitly asking them to "remember" something.
How to get better results
Good context makes a big difference. It's especially important to keep tasks clearly separated.
Start a new thread for new tasks
Every chat thread has a limited context window. The longer a thread gets, the more older content needs to be compressed. Details can get lost in the process.
That's why it's a good idea to start a new chat for new, focused, or unrelated tasks. Short, clearly defined threads work better than long threads with changing or mixed tasks.
Tip: Stick to the same thread for a related topic. For a new topic or a very long conversation, it's better to start a new one. When switching threads, ask the Agent to summarize the current status, key decisions, and open questions for the new thread.
Use Docs for recurring context
For recurring tasks, you can add context to Projects or Spaces. This can include files, instructions, and background information.
That way, you don't have to provide this context again in every new thread.
Tip: Start new threads for new tasks and store recurring context in Docs.
Say explicitly what should remain relevant
If you want the awork Agent to take something about you into account in the future, you can say so explicitly.
For example, when working on a task, you can mention that a particular preference should also be taken into account going forward.
Provide the right context
Mention relevant tasks, projects, or documents, or add them with @. You can also start the Agent directly from the relevant task or project.
This gives the Agent the right context for the work at hand.
FAQ
Does the awork Agent learn from my chats?
No. Neither the Agent nor the model learns from your chats. Across threads, only personal memories or instructions are carried over.
Why should I start a new thread for new tasks?
The longer a thread gets, the more older content needs to be compressed because of the limited context window. Details can get lost in the process. New, focused threads keep the context clear and reduce the risk of older information being lost during context compression.
Powered by happysupport.ai