Understanding how your AI agents perform is important for delivering 

, which record your agents' activities by capturing 

 to see how your agents handle tasks. If you notice an agent's response that needs improvement, you can add the input and output from that run directly to your 

. By tagging these examples appropriately, you contribute to the agent's training data, refining its performance based on 

, you can continuously enhance your agents to better serve your 

.​​​​‌﻿‍﻿​‍​‍‌‍﻿﻿‌﻿​‍‌‍‍‌‌‍‌﻿‌‍‍‌‌‍﻿‍​‍​‍​﻿‍‍​‍​‍‌﻿​﻿‌‍​‌‌‍﻿‍‌‍‍‌‌﻿‌​‌﻿‍‌​‍﻿‍‌‍‍‌‌‍﻿﻿​‍​‍​‍﻿​​‍​‍‌‍‍​‌﻿​‍‌‍‌‌‌‍‌‍​‍​‍​﻿‍‍​‍​‍​‍﻿﻿‌﻿​﻿‌﻿‌​‌﻿‌‌‌‍‌​‌‍‍‌‌‍﻿﻿​‍﻿﻿‌‍‍‌‌‍﻿‍‌﻿‌​‌‍‌‌‌‍﻿‍‌﻿‌​​‍﻿﻿‌‍‌‌‌‍‌​‌‍‍‌‌﻿‌​​‍﻿﻿‌‍﻿‌‌‍﻿﻿‌‍‌​‌‍‌‌​﻿﻿‌‌﻿​​‌﻿​‍‌‍‌‌‌﻿​﻿‌‍‌‌‌‍﻿‍‌﻿‌​‌‍​‌‌﻿‌​‌‍‍‌‌‍﻿﻿‌‍﻿‍​﻿‍﻿‌‍‍‌‌‍‌​​﻿﻿‌​﻿​‌​﻿​‌‌‍‌‍​﻿‌​​﻿‌​‌‍‌​‌‍​‌​﻿​﻿​‍﻿‌​﻿​​‌‍​‍​﻿​​​﻿‌‍​‍﻿‌​﻿‌​‌‍‌‌​﻿‌‌​﻿​​​‍﻿‌‌‍​‌​﻿​​​﻿​‌​﻿‌‍​‍﻿‌​﻿‌‍‌‍​﻿‌‍​‌​﻿‍‌‌‍​‍‌‍‌‍​﻿‌​‌‍‌‌​﻿‌‌​﻿‌﻿​﻿‍‌​﻿‍‌​﻿‍﻿‌﻿‌​‌﻿‍‌‌﻿​​‌‍‌‌​﻿﻿‌‌‍​﻿‌‍‍​‌‍​‌‌‍﻿‍‌‍‌﻿‌‍‌‌‌‍﻿​‌‍﻿﻿‌‍‌﻿‌​‍‌‌﻿‌​‌‍‌‌‌‍﻿‌​﻿‍﻿‌﻿​​‌‍​‌‌﻿‌​‌‍‍​​﻿﻿‌‌‍﻿​‌‍﻿﻿‌‍‌﻿​‍‌‌​﻿‌‌‌​​‍‌‌﻿﻿‌‍‍﻿‌‍‌‌‌﻿‍‌​‍‌‌​﻿​﻿‌​‌​​‍‌‌​﻿​﻿‌​‌​​‍‌‌​﻿​‍​﻿​‍‌‍​‌​﻿‌‍‌‍​‌​﻿​​​﻿​﻿‌‍‌‌​﻿‌‍​﻿​‍‌‍​‌‌‍​‍‌‍​‍​﻿​‍​‍‌‌​﻿​‍​﻿​‍​‍‌‌​﻿‌‌‌​‌​​‍﻿‍‌‍﻿‌‌‍‌​‌﻿‍​​﻿﻿﻿‌‍​‍‌‍​‌‌﻿​﻿‌‍‌‌‌‌‌‌‌﻿​‍‌‍﻿​​﻿﻿‌​‍‌‌​﻿​‍‌​‌‍‌﻿​﻿‌﻿‌​‌﻿‌‌‌‍‌​‌‍‍‌‌‍﻿﻿​‍‌‍‌‍‍‌‌‍‌​​﻿﻿‌​﻿​‌​﻿​‌‌‍‌‍​﻿‌​​﻿‌​‌‍‌​‌‍​‌​﻿​﻿​‍﻿‌​﻿​​‌‍​‍​﻿​​​﻿‌‍​‍﻿‌​﻿‌​‌‍‌‌​﻿‌‌​﻿​​​‍﻿‌‌‍​‌​﻿​​​﻿​‌​﻿‌‍​‍﻿‌​﻿‌‍‌‍​﻿‌‍​‌​﻿‍‌‌‍​‍‌‍‌‍​﻿‌​‌‍‌‌​﻿‌‌​﻿‌﻿​﻿‍‌​﻿‍‌​‍‌‍‌﻿‌​‌﻿‍‌‌﻿​​‌‍‌‌​﻿﻿‌‌‍​﻿‌‍‍​‌‍​‌‌‍﻿‍‌‍‌﻿‌‍‌‌‌‍﻿​‌‍﻿﻿‌‍‌﻿‌​‍‌‌﻿‌​‌‍‌‌‌‍﻿‌​‍‌‍‌﻿​​‌‍​‌‌﻿‌​‌‍‍​​﻿﻿‌‌‍﻿​‌‍﻿﻿‌‍‌﻿​‍‌‌​﻿‌‌‌​​‍‌‌﻿﻿‌‍‍﻿‌‍‌‌‌﻿‍‌​‍‌‌​﻿​﻿‌​‌​​‍‌‌​﻿​﻿‌​‌​​‍‌‌​﻿​‍​﻿​‍‌‍​‌​﻿‌‍‌‍​‌​﻿​​​﻿​﻿‌‍‌‌​﻿‌‍​﻿​‍‌‍​‌‌‍​‍‌‍​‍​﻿​‍​‍‌‌​﻿​‍​﻿​‍​‍‌‌​﻿‌‌‌​‌​​‍﻿‍‌‍﻿‌‌‍‌​‌﻿‍​​‍​‍‌﻿﻿‌

Memorang changelog

EdFlow: Monitoring and Refining Agents with Runs