Glossary

The documentation writes PentAGI terms in English in every language. This page explains what each one means.

Agent

An AI agent of PentAGI: a model with its own prompt, settings and tools that does one kind of work in a flow, such as testing, writing code or searching the web. Read more: Agents

Agent profile

In Enterprise, what defines an agent: its role, base prompt, model preset and the tools it may use. A planner chooses the profile for each subtask. Read more: Agent profiles

Agent type

The role an agent plays, such as pentester, coder or searcher. Model settings are chosen per agent type. Read more: Agents, LLM providers

Assistant

The interactive mode: you work with an agent in a chat and decide on the next step together. Read more: Your first flow

Attack chain

The sequence of steps that led to access, from the first finding to the goal of the test. Read more: Knowledge graph and analytics, Reports

Automation

The autonomous mode: PentAGI plans and runs a flow on its own, from the goal to the report. Read more: Your first flow

Company

Your organization's account in the PentAGI Console.

Customer

The client who receives the pentest and its report. Read more: Reports

Engagement

The work a security team delivers to its client, such as a penetration test of the client's systems. Each PentAGI run within it is a flow. Read more: Autonomous penetration testing

Finding

Something the test discovered and recorded, such as a host, a running service or a vulnerability. Read more: Knowledge graph and analytics, Reports

Flow

One run of PentAGI: a goal, the tasks created from your messages, and everything the agents did along the way. Read more: Your first flow, Agents

Knowledge base

The documents that agents can search, kept in the vector store. Read more: Embeddings

The graph of hosts, services, vulnerabilities and the access between them that PentAGI builds during a test when this optional feature is enabled. It shows how findings connect. Read more: Knowledge graph and analytics, Memory and knowledge

MCP server

In Enterprise, a server that speaks the Model Context Protocol and gives agents additional tools. Read more: Plugins and MCP

Memory

What agents keep so they can build on earlier work instead of starting from scratch: long-term, working and episodic memory. Read more: Memory and knowledge, Embeddings

Pentest

A penetration test: an authorized attempt to break into systems in order to find their weaknesses. Read more: Autonomous penetration testing

Plugin

In Enterprise, a package in the open Agent Plugins format that adds skills, MCP servers and agent profiles. Read more: Plugins and MCP

Provider

A service or server that gives PentAGI its language models, such as OpenAI, Anthropic or a local Ollama. Read more: LLM providers

Report

The document PentAGI writes about a flow and its findings. In Enterprise, it is a customer-ready document built from a template. Read more: Reports, Your first flow

Sandbox

The isolated Docker container in which agents run their tools. The interface shows it as Terminal. Read more: Architecture, Worker node

Search engine

A web search service that agents use to gather fresh information, such as DuckDuckGo, Google or Tavily. Read more: Search engines

Sub-agent

In Enterprise, an agent that a working agent starts for parallel work inside a subtask. Read more: Agent profiles

Subtask

One step of a task. PentAGI plans the subtasks of each task and adjusts them as the work goes on. Read more: Agents, Your first flow

Task

One request in a flow: its first message, or a later message that does not answer an agent's question. PentAGI splits each task into subtasks. Read more: Agents, Your first flow

Template

Saved text that PentAGI reuses. A template saved in Templates fills in the first message of a new flow; in Enterprise, a report template sets the sections of a report and their order, so different templates produce different documents for the customer, the engineers and management. Read more: Your first flow, Reports