From cdaec5768df6719a9f1729ce42606c6da326c70d Mon Sep 17 00:00:00 2001 From: Eric Burel Date: Thu, 19 Mar 2026 13:57:34 +0100 Subject: [PATCH] docs: Enhance AI agent description in intro tutorial (#4228) Co-authored-by: Rowena Jones <36301604+RoRoJ@users.noreply.github.com> --- docs/advanced-ai/intro-tutorial.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/advanced-ai/intro-tutorial.md b/docs/advanced-ai/intro-tutorial.md index 538d85766..541037309 100644 --- a/docs/advanced-ai/intro-tutorial.md +++ b/docs/advanced-ai/intro-tutorial.md @@ -32,17 +32,17 @@ Many people find it easier to take in new information in video format. This tuto If you're already familiar with AI, feel free to skip this section. This is a basic introduction to AI concepts and how they can be used in n8n workflows. -An [AI agent](/glossary.md#ai-agent) builds on [Large Language Models (LLMs)](/glossary.md#large-language-model-llm), which generate text based -on input by predicting the next word. While LLMs only process input to produce -output, AI agents add goal-oriented functionality. They can use [tools](/glossary.md#ai-tool), process -their outputs, and make decisions to complete tasks and solve problems. +An [AI agent](/glossary.md#ai-agent) builds on [Large Language Models (LLMs)](/glossary.md#large-language-model-llm). LLMs generate text based +on input by predicting the next word. They can be used to select the best tool to achieve a task, or even simulate complex decision-making, but they can't act on decisions or use tools themselves. +AI agents add goal-oriented functionality. They can use [tools](/glossary.md#ai-tool), act on +their outputs, complete tasks and solve problems. In n8n, the AI agent is represented as a node with some extra connections. | Feature | LLM | AI Agent | |---------------------|----------------------------|------------------------------------| | Core Capability | Text generation | Goal-oriented task completion | -| Decision-Making | None | Yes | +| Decision-Making | Simulates choices in text | Selects and executes actions | | Uses Tools/APIs | No | Yes | | Workflow Complexity | Single-step | Multi-step | | Scope | Generates language | Performs complex, real-world tasks |