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

# Findings and evidence

> Read a BotGauge finding: what happened, the rule it breaks, the exact attack and reply, the tool call, the policy decision, and how it was decided.

A finding is a recorded problem. Open one from an agent's Open breaches list or from a report with **View** or **Open finding**.

## The header

The header shows the severity, how many tries reproduced it ("3 of 3 tries, happened 3 times"), the result (for example **Confirmed finding**), the finding ID with a **Copy** button, and a title such as "Refund of \$240 issued after a manager claim".

## What happened

A plain-language description of the problem, with a suggested fix. For example: require a recorded approval before the refund tool is called for more than the limit, whoever the user says they are.

## Why this violates your rule

The rule text and its revision number. Rules are versioned, so a finding always points to the exact rule version it broke.

## Proof

The proof is one attack, with how often it reproduced, and a **Copy** button.

| Part | What it shows |
| - | - |
| Attacker asked | The exact message BotGauge sent |
| Your rule says | The rule being tested |
| Agent replied | The agent's reply |
| Requested | The tool call the agent made, with its arguments |
| Policy decision | Whether the action violated the rule, and why |
| Execution attempted | Whether the tool call ran, and whether that is agent-reported or confirmed |
| Tool reported | What the tool returned |
| Backend check | Whether BotGauge verified the effect itself. If not, the page says what to connect so it can. |
| Decided by | What decided the verdict, for example "Policy on execution, strong oracle" |

### The conversation

Switch between **Minimal** and **Full** to see only the turns that matter or the whole exchange. Card numbers and secrets in replies are masked.

## Attempts

Every attempt for the rule is listed with its technique and whether it **Broke through** or **Held**. Each one opens the full conversation, tool calls, and trace, and lets you run it again.

## Strength of the evidence

A finding decided by a tool call or backend check is stronger than one judged only from the agent's reply. If BotGauge could not read the effect itself, the Backend check shows "Not checked", and the page says which capability would let it. Connecting a verifier or trace reader is how you move a **Likely** breach to a confirmed one. See [black box and grey box](https://www.botgauge.com/docs/red-teaming/black-box-and-grey-box.md).

Read the full evidenceOpen any finding to see the attack, reply, and tool calls in [BotGauge](https://cloud.botgauge.com).

[Open a finding →](https://cloud.botgauge.com)

## Next

After you fix the agent, replay the attack to confirm the fix. See [Fix, verify, compare, and export](https://www.botgauge.com/docs/red-teaming/fix-and-verify.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.