> For the complete documentation index, see [llms.txt](https://doc.threatreaper.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.threatreaper.ai/user-guide/ai-explain-ai-explainability.md).

# 💡 AI-Explain — AI Explainability

**Menu:** GOVERNANCE > AI-Explain.

Lists decisions and findings from three sources and explains them: AI-Firewall (input guard decisions), AI-Probe (adversarial scan vulnerabilities), and AI-Discover (asset risk scores). Open an item to see feature-importance bars (top contributing terms or features and a confidence value) so you can understand why a prompt was blocked or an asset was rated risky. Filter by source and export results.

## 11.1 How to configure it

There's no setup required — AI-Explain reads automatically from the other modules. Use the filters to narrow what you see:

* **Source** — All, AI-Firewall, AI-Probe, or AI-Discover
* **Decision** — threats only, or safe/allowed only
* **Guardrail** — a specific detector (for example PII, Prompt Injection, Toxicity)
* **Search** — free-text search across prompts and results

## 11.2 Errors you might see and how to fix them

| **Message**                 | **What it means**                                                  | **What to do**                                                                        |
| --------------------------- | ------------------------------------------------------------------ | ------------------------------------------------------------------------------------- |
| "No data available"         | None of the three source modules have results yet for your project | Run a scan in AI-Probe, enable AI-Discover, or send traffic through AI-Firewall first |
| "No matching results found" | Your filters are too narrow                                        | Clear or widen the Source/Decision/Guardrail filters                                  |

## 11.3 What success looks like

Opening a blocked prompt shows a clear breakdown:

```
Source: AI-Firewall (Input Guard)
Decision: BLOCK

Guardrail: Prompt Injection
Confidence: 88%

Top contributing features:

prompt_injection ████████░ 0.145

jailbreak ███████░ 0.089

bias ████░ 0.042

Interpretation: Threat-indicating tokens detected

Recommendation: Block — high agreement across detection methods
```

Each record also shows the username, risk level, timestamp, and which guardrails were triggered, so you can explain any decision to an auditor or end user.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://doc.threatreaper.ai/user-guide/ai-explain-ai-explainability.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.