mirror of
https://github.com/prowler-cloud/prowler.git
synced 2026-01-25 02:08:11 +00:00
6c01151d78
Co-authored-by: Chandrapal Badshah <12944530+Chan9390@users.noreply.github.com> Co-authored-by: Rubén De la Torre Vico <ruben@prowler.com> Co-authored-by: Andoni Alonso <14891798+andoniaf@users.noreply.github.com>
63 lines
2.7 KiB
Plaintext
63 lines
2.7 KiB
Plaintext
---
|
|
title: 'How It Works'
|
|
---
|
|
|
|
import { VersionBadge } from "/snippets/version-badge.mdx"
|
|
|
|
<VersionBadge version="5.8.0" />
|
|
|
|
Prowler Lighthouse AI integrates Large Language Models (LLMs) with Prowler security findings data.
|
|
|
|
Behind the scenes, Lighthouse AI works as follows:
|
|
|
|
- Lighthouse AI runs as a [Langchain agent](https://docs.langchain.com/oss/javascript/langchain/agents) in NextJS
|
|
- The agent connects to the configured LLM provider to understand the prompt and decide what data is needed
|
|
- The agent accesses Prowler data through [Prowler MCP](https://docs.prowler.com/getting-started/products/prowler-mcp), which exposes tools from multiple sources, including:
|
|
- Prowler Hub
|
|
- Prowler Docs
|
|
- Prowler App
|
|
- Instead of calling every tool directly, the agent uses two meta-tools:
|
|
- `describe_tool` to retrieve a tool schema and parameter requirements.
|
|
- `execute_tool` to run the selected tool with the required input.
|
|
- Based on the user's query and the data necessary to answer it, Lighthouse agent will invoke necessary Prowler MCP tools using `discover_tool` and `execute_tool`
|
|
|
|
<Note>
|
|
Lighthouse AI supports multiple LLM providers including OpenAI, Amazon Bedrock, and OpenAI-compatible services. For configuration details, see [Using Multiple LLM Providers with Lighthouse](/user-guide/tutorials/prowler-app-lighthouse-multi-llm).
|
|
</Note>
|
|
|
|
<img className="block dark:hidden" src="/images/lighthouse-architecture-light.png" alt="Prowler Lighthouse Architecture" />
|
|
<img className="hidden dark:block" src="/images/lighthouse-architecture-dark.png" alt="Prowler Lighthouse Architecture" />
|
|
|
|
|
|
<Note>
|
|
Lighthouse AI can only read relevant security data. It cannot modify data or access sensitive information such as configured secrets or tenant details.
|
|
|
|
</Note>
|
|
|
|
## Set Up
|
|
|
|
Getting started with Prowler Lighthouse AI is easy:
|
|
|
|
1. Navigate to **Configuration** → **Lighthouse AI**
|
|
2. Click **Connect** under the desired provider (OpenAI, Amazon Bedrock, or OpenAI Compatible)
|
|
3. Enter the required credentials
|
|
4. Select a default model
|
|
5. Click **Connect** to save
|
|
|
|
<Note>
|
|
For detailed configuration instructions for each provider, see [Using Multiple LLM Providers with Lighthouse](/user-guide/tutorials/prowler-app-lighthouse-multi-llm).
|
|
</Note>
|
|
|
|
<img src="/images/prowler-app/lighthouse-configuration.png" alt="Lighthouse AI Configuration" />
|
|
|
|
### Adding Business Context
|
|
|
|
The optional business context field lets teams provide additional information to help Lighthouse AI understand environment priorities, including:
|
|
|
|
- Organization cloud security goals
|
|
- Information about account owners or responsible teams
|
|
- Compliance requirements
|
|
- Current security initiatives or focus areas
|
|
|
|
Better context leads to more relevant responses and prioritization that aligns with your needs.
|