What is an agent?
An agent is a chat session that can work independently. Each agent:- Has its own conversation history
- Can be assigned tasks
- Can attach to a notebook to write and run research code
Starting an agent
Start your first agent from the chat composer. You can also create agents from within a conversation when you need parallel work. Execution mode applies to every agent. Choose Notebook in Settings > Agents for interactive notebook work or Script for standalone files and shell-driven jobs. Agents created by other agents inherit the same mode.Parallel agents
The biggest time sink in research is sequential experimentation — you try one thing, wait, check results, then try the next. Qualia eliminates that by running multiple agents in parallel.Example: model comparison
Ask Qualia:“Compare three approaches: (1) random forest with default hyperparameters, (2) XGBoost with early stopping, and (3) a small neural network. Use 5-fold cross-validation for each. Run them in parallel.”Qualia creates three agents, each working on one approach simultaneously. When they finish, you can compare results side by side. Use the Parallelism research-style control in chat or under Settings > Agents to choose how readily Qualia splits suitable work across agents. Low usually keeps work in one agent, Medium delegates when useful, and High proactively looks for parallel work.
Example: hyperparameter sweep
“Try learning rates of 0.001, 0.01, and 0.1 with the current model. Train each for 50 epochs and compare validation loss curves.”
Example: feature engineering
“Test three feature sets: (1) just the raw numeric columns, (2) with polynomial features, (3) with target encoding on categoricals. See which gives the best F1 score.”
The Agents sidebar
The Agents sidebar lists new chats and chats you or teammates have messaged first. Other agents appear under Agent-driven; click its arrow to collapse or expand the group.- Activity: A spinner means the agent is working. A bell means it needs input or approval. Idle agents show when they last updated.
- Requests: Hover over a waiting agent to see its full question or command. The chat creator can accept or reject command approvals.
- Tasks: Assigned tasks appear beneath the agent. Hover over a summary to see additional tasks, and open Project for details.
Agent actions
From the sidebar, you can:- Open: Jump to an agent’s conversation
- Stop / Resume: Use the header controls to stop running agents or resume stopped ones. In Cloud, workspace owners can stop all agents; other members can stop their own. Bulk resume applies to your own chats.
- Delete: Remove the agent and its history
- Select agents: Cmd/Ctrl-click or Shift-click an agent, or right-click and choose Select agent. Use the checkboxes to select agents, then Delete to remove them. Press Escape to leave selection mode
Dragging agents into tabs
Agent cards work like tab handles. Drag a card out of the sidebar to place that agent’s conversation exactly where you want it:- Onto a tab bar to open the conversation as a tab there — drop between tabs to choose its position
- Toward the edge of the editor area to open it in a new split
- Onto a chat composer to mention that agent in the message instead
Agent communication
Agents can communicate with each other:- Message agent: One agent can send a message to another
- Agent links: Click to navigate between related agents in chat
- Shared knowledge: All agents in the workspace share the Knowledge System
Agent confirmation
When an agent wants to create a new parallel agent, it can require your approval first. This is controlled in Settings > Agents:- Enabled: New agents wait for you to approve
- Disabled: Agents start immediately
Integration with tasks
Agents work on tasks:- Tasks can be assigned to specific agents
- Agents work through their task queue