Summary

This update adds call transcripts to the AI Agent tools, introduces a feedback flow in execution logs, and includes general reliability fixes.

What’s included

Call transcripts (built in)

The AI Agent action now includes a built-in call transcript tool. It gives the agent access to a contact’s call history without additional setup.

To use it, reference call transcripts in your agent prompt. The agent can retrieve transcripts and use them as context when making decisions or writing responses.

This works alongside conversation history, so the agent can use both chat messages and calls for a more complete view of each contact interaction.

Feedback flow in execution logs

You can now submit structured feedback on each AI Agent run directly from the execution logs. This makes it easier to flag issues, document what worked, and share specifics for each run.

Bug fixes and stability improvements

Several fixes were made across the AI Agent action to improve reliability and overall performance.

Why this matters

With access to both chat history and call transcripts, the AI Agent can respond with better context. The new feedback flow helps teams identify gaps faster and improve future runs.