Skip to main content

The Execution Interface

When you run an automation, you’re taken to the Agent Run page. This is where you watch, interact, and control the execution.

Interface Layout

Video Panel

Live stream of the Windows desktop

Chat Panel

Action-by-action log and HITL controls

Progress Bar

Current stage of execution

Control Bar

Play, pause, cancel buttons

Live Video Streaming

The left side shows a real-time video of the Windows desktop:
  • WebRTC powered - Low latency, high quality
  • Full screen option available
  • Screenshot button to capture current view
Video streaming requires WebRTC support in your browser. Most modern browsers work fine.

Chat Panel

The right side shows the conversation with the AI agent:
Agent: Starting automation "Weekly Sales Report"
       Connecting to driver machine...

Agent: Connected. Opening Excel application.
       [Screenshot captured]

Agent: I'm about to click "File > Open"
       [Approve] [Modify] [Skip] [Cancel]

You: [Clicked Approve]

Agent: Opening file dialog. Navigating to Sales folder...

HITL Controls

When the agent pauses for approval, you’ll see these options:
When to use: The action looks correctClick Approve to let the agent proceed with the planned action.

Progress Stages

The progress bar shows where you are in the execution:
StageDescription
QueuedWaiting for an available driver
ConnectingEstablishing connection to driver
RunningActively executing steps
WaitingPaused for HITL approval
CompletedFinished successfully
FailedEncountered an error
CancelledStopped by user

Screenshots

Throughout execution, Granite captures screenshots:
  • Before each action
  • After each action
  • On errors for debugging
  • Final state when complete
View screenshots in the slideshow below the video panel.

Recordings

Every execution is recorded:
  • Full video from start to finish
  • Downloadable after completion
  • Useful for auditing and review

Execution Controls

Pause

Temporarily stop execution (resume later)

Cancel

Stop execution permanently

Full Screen

Maximize the video panel

Handling Errors

If something goes wrong:
  1. Video shows the error state - See exactly what happened
  2. Chat explains the error - Agent describes what went wrong
  3. Options to recover:
    • Modify the approach and retry
    • Skip the problematic step
    • Cancel and investigate
If the agent repeatedly fails on the same action, it may need a different approach. Try modifying the instruction or creating an RPA script for more control.

After Execution

When the run completes:
  • Summary - Success/failure, duration, action count
  • Screenshots - Browse all captured images
  • Recording - Download the video
  • Logs - Detailed trace of every step

Tips for Effective Monitoring

The video shows exactly what the agent sees. If something looks wrong, you can catch it immediately.
The agent explains what it’s about to do before doing it. This is your chance to catch mistakes.
If an action is close but not quite right, modify it instead of cancelling. You’ll preserve progress.
Even if execution succeeds, watch the recording to understand how the automation works. You might find optimization opportunities.

Keyboard Shortcuts

ShortcutAction
EnterApprove current action
EscapeCancel execution
SpacePause/Resume

Next Steps