docs: Enhance AI agent description in intro tutorial

[eric-burel]

AI generated summary: clarified the role of AI agents and their relation to LLMs, emphasizing their decision-making capabilities and tool selection.

Hi folks,

Minor nit but I'd like to clarify that it's the LLM that makes decisions in an agent loop. This is important with regards to understanding bias : all biases that apply to an LLM can spread to an agent.

I often use the metaphor of an expert on the phone : the LLM is the expert, it can talk to you but also tell you exactly what to do, decide the next steps and so on. Only, it's on the phone, so it can't do anything itself: the agent is responsible of actually acting, hence its name.

---

Summary by cubic

Clarified the roles of LLMs and agents in the intro tutorial to avoid confusion about who decides and who acts. The text now states that the LLM selects tools and makes decisions, while the agent executes actions to achieve the goal.

^{Written for commit d8e724a. Summary will update on new commits.}

[netlify]

✅ Deploy Preview for n8n-docs ready!

Name	Link
🔨 Latest commit	d8e724a
🔍 Latest deploy log	https://app.netlify.com/projects/n8n-docs/deploys/698db55c30a2f2000859d306
😎 Deploy Preview	https://deploy-preview-4228--n8n-docs.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[cubic-dev-ai]

1 issue found across 1 file

Prompt for AI agents (all issues)

Check if these issues are valid — if so, understand the root cause of each and fix them.


<file name="docs/advanced-ai/intro-tutorial.md">

<violation number="1" location="docs/advanced-ai/intro-tutorial.md:36">
P3: The new description says LLMs can select tools and make complex decisions, but the comparison table immediately below still lists LLM decision-making as "None" and tool usage as "No." This contradiction could confuse readers and should be reconciled.</violation>
</file>

---

Since this is your first cubic review, here's how it works:

• cubic automatically reviews your code and comments on bugs and improvements
• Teach cubic by replying to its comments. cubic learns from your replies and gets better over time
• Add one-off context when rerunning by tagging @cubic-dev-ai with guidance or docs links (including llms.txt)
• Ask questions if you need clarification on any suggestion

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[cubic-dev-ai]

P3: The new description says LLMs can select tools and make complex decisions, but the comparison table immediately below still lists LLM decision-making as "None" and tool usage as "No." This contradiction could confuse readers and should be reconciled.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At docs/advanced-ai/intro-tutorial.md, line 36:

<comment>The new description says LLMs can select tools and make complex decisions, but the comparison table immediately below still lists LLM decision-making as "None" and tool usage as "No." This contradiction could confuse readers and should be reconciled.</comment>

<file context>
@@ -32,10 +32,10 @@ Many people find it easier to take in new information in video format. This tuto
-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, but they can also be used to select the best tool to achieve a task, or even make complex decisions.
+While LLMs only process input to produce text or JSON output, AI agents add goal-oriented functionality. They can use [tools](/glossary.md#ai-tool), process
+their outputs, complete tasks and solve problems.
</file context>