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

# How DeepBlocker tests people and agents

> A two-minute explanation of the two products, who runs each one, and what you see at the end.

Criminals now use AI voices and AI chat to trick staff and to trick the AI agents that companies put in front of customers. DeepBlocker runs the same tricks against you first, with your written permission, so you find the weak spots before a criminal does.

## The two products

| Product | Who is tested | Who runs it | What you get |
| - | - | - | - |
| Vishing simulation | Your own staff, by phone | Your security team, in the console | A verdict per person, a transcript and a recording per call, a report for your auditor |
| Agent Assurance | Your AI agent, over web, API or Telegram | DeepBlocker, as a managed engagement | A report with findings, each with an exposure band and proof of what the agent did |

```mermaid theme={null}
flowchart LR
  A[Your security team] -->|authorises and launches| B[DeepBlocker console]
  B -->|calls| C[Your staff]
  C -->|results| B
  D[DeepBlocker analysts] -->|attack| E[Your AI agent]
  E -->|evidence| F[Published report]
  B --> G[You read the results]
  F --> G
```

## Vishing simulation, in short

1. You add the people to call, with their consent recorded.
2. You create an attacker: a name, a story, a voice and an opening line.
3. You build a campaign, name the person who authorised it, and launch.
4. The attacker calls each person and tries to get what a criminal would ask for.
5. Each call is graded Passed, Failed or Reported. You read the transcript and the recording.

Before any real person is called, you can take the call yourself in your browser. See [Take a test call in your browser](https://docs.deepblocker.ai/vishing/campaigns/test-call.md).

## Agent Assurance, in short

You connect a test build of your agent to us. We register it, write the rules it must not break, and run attack conversations against it. The report says, for each rule, whether the agent held, tried to break it, or broke it with proof. You read the report in the console.

## What you see at the end

Both products end in the console. For vishing, see [Read your results](https://docs.deepblocker.ai/vishing/results/overview.md) and [Export for auditors](https://docs.deepblocker.ai/vishing/results/auditor-pack.md). For Agent Assurance, your reports appear under **Agent Assurance** in the sidebar once we publish them.

> [card] [Before you test anyone](https://docs.deepblocker.ai/before-you-start.md)
>
> Who must authorise a campaign, and what consent you need.

> [card] [Your first 15 minutes](https://docs.deepblocker.ai/quickstart.md)
>
> Add a voice, create an attacker, build a campaign, take the test call.

> [card] [Words we use](https://docs.deepblocker.ai/glossary.md)
>
> The terms you will meet in the console.


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