> ## Documentation Index
> Fetch the complete documentation index at: https://docs.egma.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Review production conversations

Open **Traces** in your project to inspect conversations received from your agent.

## Read a conversation

The **Traces** table shows the agent, time, duration, p90 turn latency,
and trace ID when those values are available. Select a trace to open its
details and inspect the transcript, metrics, and grades.

To grade incoming conversations, [configure graders](/docs/platform/graders/configure-graders)
with production scope and the sample percentage you want. A missing grade can
mean the conversation was outside that scope or sample, is still processing,
or could not be graded. Check its grading state before treating it as a pass.

Each grade has its own score and threshold. A combined score summarizes the
selected grades; it does not decide an overall pass or fail. See
[Scores and thresholds](/docs/platform/graders/scores-and-thresholds).

## Turn a finding into a test

When a production conversation exposes a problem, [create a test](/docs/platform/tests/create-a-test) with the same situation and the behavior you expected. Use test data in place of caller details. Add it to a regression suite after fixing the agent.