QA
QA node allows you to run post-call quality analysis on your Voice Agent runs
The QA node lets you define quality analysis criteria that are automatically evaluated after each call ends. Use it to score agent performance, check compliance, or extract structured insights from conversations.
Creating a QA Node#
You can add a QA node to your workflow from the Voice Agent Builder. Once added, configure the analysis criteria that you want to evaluate for each call.
Viewing QA Results#
After a call completes, the QA analysis runs automatically. You can view the results on the Run Detail page for each individual run.
When to use QA#
Use QA when you need consistent post-call checks for compliance, lead quality, agent behavior, outcome tracking, or internal review.
Good QA criteria#
- Ask for observable outcomes that can be judged from the transcript or run data.
- Keep each criterion focused on one thing, such as consent, qualification, escalation, or summary quality.
- Use clear pass/fail or scoring language so results are easy to review across many runs.
Operational workflow#
After calls complete, review QA output together with transcripts, recordings, gathered context, and run status. Use repeated failures to improve prompts, pathways, or tool configuration.