Workflow or AI Agent? The 5-Question Test I Use Before Adding an LLM Node

Description and use

A five‑question test guides whether to use a plain workflow, a single LLM step, or an AI agent in n8n. The outcome is a fixed workflow with one structured LLM call, a parse node, and deterministic IF/Switch logic.

Problem

Deciding whether to use a plain workflow, a single LLM step, or an AI agent in n8n automations.

Outcome

Using the five‑question test consistently produces deterministic workflows with a single LLM step, avoiding the risks of full AI agents while still leveraging LLMs for parsing messy text.

Workflow

• 1. Trigger (Webhook or Schedule)
• 2. Config (Code node) – set baseUrl and model
• 3. Build Prompt (Code node) – strict system prompt with JSON schema
• 4. LLM (HTTP Request) – POST to chat/completions with response_format json_object and low temperature
• 5. Parse (Code node) – extract JSON, validate, handle errors
• 6. Decide (IF/Switch) – deterministic rules on parsed fields

Evidence

Every one of my workflows ends the LLM step with the same small Parse node: …

Source

If I can describe the decision as a rule a new hire could follow without judgment, it doesn't need a model.

Source

Models are good at turning unstructured text into structured fields: a review into sentiment plus topics, a meeting transcript into decisions and owners, a PDF invoice into vendor, totals and line items.

Source