# Glossary

> The PentAGI terms used across the documentation and what each one means.

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

## [Agent](https://pentagi.com/docs/glossary/#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](https://pentagi.com/docs/concepts/agents/)

## [Agent profile](https://pentagi.com/docs/glossary/#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](https://pentagi.com/docs/enterprise/agent-profiles/)

## [Agent type](https://pentagi.com/docs/glossary/#agent-type)

The role an agent plays, such as pentester, coder or searcher. Model settings are chosen per agent type. Read more: [Agents](https://pentagi.com/docs/concepts/agents/), [LLM providers](https://pentagi.com/docs/configuration/llm-providers/)

## [Assistant](https://pentagi.com/docs/glossary/#assistant)

The interactive mode: you work with an agent in a chat and decide on the next step together. Read more: [Your first flow](https://pentagi.com/docs/getting-started/first-flow/)

## [Attack chain](https://pentagi.com/docs/glossary/#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](https://pentagi.com/docs/enterprise/knowledge-graph/), [Reports](https://pentagi.com/docs/enterprise/reports/)

## [Automation](https://pentagi.com/docs/glossary/#automation)

The autonomous mode: PentAGI plans and runs a flow on its own, from the goal to the report. Read more: [Your first flow](https://pentagi.com/docs/getting-started/first-flow/)

## [Company](https://pentagi.com/docs/glossary/#company)

Your organization's account in the PentAGI Console.

## [Customer](https://pentagi.com/docs/glossary/#customer)

The client who receives the pentest and its report. Read more: [Reports](https://pentagi.com/docs/enterprise/reports/)

## [Engagement](https://pentagi.com/docs/glossary/#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](https://pentagi.com/docs/concepts/autonomous-pentesting/)

## [Finding](https://pentagi.com/docs/glossary/#finding)

Something the test discovered and recorded, such as a host, a running service or a vulnerability. Read more: [Knowledge graph and analytics](https://pentagi.com/docs/enterprise/knowledge-graph/), [Reports](https://pentagi.com/docs/enterprise/reports/)

## [Flow](https://pentagi.com/docs/glossary/#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](https://pentagi.com/docs/getting-started/first-flow/), [Agents](https://pentagi.com/docs/concepts/agents/)

## [Knowledge base](https://pentagi.com/docs/glossary/#knowledge-base)

The documents that agents can search, kept in the vector store. Read more: [Embeddings](https://pentagi.com/docs/configuration/embeddings/)

## [Knowledge graph](https://pentagi.com/docs/glossary/#knowledge-graph)

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](https://pentagi.com/docs/enterprise/knowledge-graph/), [Memory and knowledge](https://pentagi.com/docs/concepts/memory/)

## [MCP server](https://pentagi.com/docs/glossary/#mcp-server)

In Enterprise, a server that speaks the Model Context Protocol and gives agents additional tools. Read more: [Plugins and MCP](https://pentagi.com/docs/enterprise/plugins-and-mcp/)

## [Memory](https://pentagi.com/docs/glossary/#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](https://pentagi.com/docs/concepts/memory/), [Embeddings](https://pentagi.com/docs/configuration/embeddings/)

## [Pentest](https://pentagi.com/docs/glossary/#pentest)

A penetration test: an authorized attempt to break into systems in order to find their weaknesses. Read more: [Autonomous penetration testing](https://pentagi.com/docs/concepts/autonomous-pentesting/)

## [Plugin](https://pentagi.com/docs/glossary/#plugin)

In Enterprise, a package in the open Agent Plugins format that adds skills, MCP servers and agent profiles. Read more: [Plugins and MCP](https://pentagi.com/docs/enterprise/plugins-and-mcp/)

## [Provider](https://pentagi.com/docs/glossary/#provider)

A service or server that gives PentAGI its language models, such as OpenAI, Anthropic or a local Ollama. Read more: [LLM providers](https://pentagi.com/docs/configuration/llm-providers/)

## [Report](https://pentagi.com/docs/glossary/#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](https://pentagi.com/docs/enterprise/reports/), [Your first flow](https://pentagi.com/docs/getting-started/first-flow/)

## [Sandbox](https://pentagi.com/docs/glossary/#sandbox)

The isolated Docker container in which agents run their tools. The interface shows it as Terminal. Read more: [Architecture](https://pentagi.com/docs/concepts/architecture/), [Worker node](https://pentagi.com/docs/deployment/worker-node/)

## [Search engine](https://pentagi.com/docs/glossary/#search-engine)

A web search service that agents use to gather fresh information, such as DuckDuckGo, Google or Tavily. Read more: [Search engines](https://pentagi.com/docs/configuration/search-engines/)

## [Sub-agent](https://pentagi.com/docs/glossary/#sub-agent)

In Enterprise, an agent that a working agent starts for parallel work inside a subtask. Read more: [Agent profiles](https://pentagi.com/docs/enterprise/agent-profiles/)

## [Subtask](https://pentagi.com/docs/glossary/#subtask)

One step of a task. PentAGI plans the subtasks of each task and adjusts them as the work goes on. Read more: [Agents](https://pentagi.com/docs/concepts/agents/), [Your first flow](https://pentagi.com/docs/getting-started/first-flow/)

## [Task](https://pentagi.com/docs/glossary/#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](https://pentagi.com/docs/concepts/agents/), [Your first flow](https://pentagi.com/docs/getting-started/first-flow/)

## [Template](https://pentagi.com/docs/glossary/#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](https://pentagi.com/docs/getting-started/first-flow/), [Reports](https://pentagi.com/docs/enterprise/reports/)

## [Tenant](https://pentagi.com/docs/glossary/#tenant)

One PentAGI installation. When several installations share external resources, such as one PostgreSQL database, each one you add gets its own TENANT\_ID; an existing installation keeps it empty. Read more: [Production](https://pentagi.com/docs/deployment/production/)

## [Tool](https://pentagi.com/docs/glossary/#tool)

What an agent acts through: a built-in capability such as the terminal, the isolated browser or web search, or a program in the sandbox such as nmap, metasploit or sqlmap. Read more: [Agents](https://pentagi.com/docs/concepts/agents/), [Architecture](https://pentagi.com/docs/concepts/architecture/)

## [Tool call](https://pentagi.com/docs/glossary/#tool-call)

A request from the model to run one of the agent's tools, such as a terminal command or a web search. Read more: [Agents](https://pentagi.com/docs/concepts/agents/), [Troubleshooting](https://pentagi.com/docs/deployment/troubleshooting/)

## [Vector store](https://pentagi.com/docs/glossary/#vector-store)

The database of embeddings that lets agents search memory and documents by meaning. Read more: [Memory and knowledge](https://pentagi.com/docs/concepts/memory/), [Embeddings](https://pentagi.com/docs/configuration/embeddings/)

## [Worker node](https://pentagi.com/docs/glossary/#worker-node)

A separate server that runs the agents' tool containers, so the commands they run never touch the main PentAGI host. Read more: [Worker node](https://pentagi.com/docs/deployment/worker-node/)