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

# Audit an agent

> Investigate one agent end to end — its activity trends, recent calls, its system prompt, and open findings.

When one agent looks off, this is how you dig in — from its activity trends down
to the calls and [findings](/docs/findings) behind them.

## 1. Open the agent

From [Agents](/docs/agents), open the agent. The detail page shows a call-volume
trend chart and an hour-by-day heatmap, so you can tell whether today's dip is a
blip or a trend.

## 2. Drill into the calls

The detail page lists the agent's most recent [conversations](/docs/conversations).
Open a call to read the transcript next to the system prompt and listen to the
recording. To narrow in, filter the conversations by ended reason, has-audio, or
date range. The agent's **system prompt** (and its flow) are on the detail tabs
too, so you can check its behavior against what it was actually told to do.

## 3. Work the findings

When open [findings](/docs/findings) for an agent pile up, the agent surfaces a prompt
to review them. From there, [triage](/docs/guides/triage-findings) the findings and
capture a [solution](/docs/solutions) for the fix.

## Audit programmatically

* **[MCP](/docs/mcp)** — `get_agent`, `list_conversations`, and `query_database` for
  ad-hoc aggregations over the agent's calls (e.g. failure counts by ended
  reason).

## Related

* [Agents](/docs/agents) — the concepts behind an audit.
* [Conversations](/docs/conversations) — the calls you're drilling into.
* [Findings](/docs/findings) — the recurring issues you promote and fix.