Human-in-the-loop features to maintain user oversight and agency.
Have the AI show the steps it will take to respond to the user's prompt before it executes its response
Support iterative prompting while retaining footprints band visibility back to the original
Lets the AI give inline annotations to cite its sources
Manage the flow of information or pause a request mid-stream to adjust the prompt
Help users proactively modulate compute power through transparent cost estimates for actions
Support exploration and iterative prompting while reducing compute costs until a final form is ready
Control what details the AI knows about you
See and manage what additional sources the AI references to generate its response
Confirm the user's intent for complicated prompts
Live visibility into the AI's action in a shared canvas or workspace
Reveals the AI's logic thought process, tool use, and decisions for oversight and auditability
Trace through multiple variations of a result to choose the one that works best for them
Allow users to confirm AI decisions and actions before proceeding
