# How to Stop ChatGPT from Making Things Up: 5 Guardrails > Stop ChatGPT from making things up with five guardrails: a facts list, a Not stated rule, never-invent rules, a closed category list and a final check. Source: https://learn.ynteractive.com/content/blog/stop-chatgpt-making-things-up · Updated 2026-10-01 · Free from Stepthrough (https://learn.ynteractive.com) By [Robert Breen](https://learn.ynteractive.com/content/about) · Published October 1, 2026 · Updated October 1, 2026 · 6 min read ChatGPT · Prompts · n8n You can't switch off ChatGPT's habit of filling gaps, but you can make it much rarer with five [guardrails](https://learn.ynteractive.com/content/glossary/guardrails): give it a numbered list of facts, tell it what to write when something is missing, add "never make up" rules, limit its choices to a fixed list, and check the result before it goes out. This guide is for anyone who uses ChatGPT or an [AI agent](https://learn.ynteractive.com/content/glossary/ai-agent) for work emails and records, and each guardrail comes from a free lesson, starting with [Reply Faster: Customer Emails](https://learn.ynteractive.com/content/chatgpt-reply-to-customer-emails). ## Why does ChatGPT make things up? ChatGPT writes the most likely next words, so when your [prompt](https://learn.ynteractive.com/content/glossary/prompt) leaves a gap, it fills the gap with something that sounds right. The common name for this is "hallucination": a confident answer that isn't based on anything you gave it. The lessons show it in small, realistic ways. A vague prompt gets an email with "[Your Company Name]" and other blanks. A careful-sounding customer reply calls a cake "completely nut-free" when the bakery never said so. A meeting summary would happily give every task a due date, whether or not anyone said one. Each guardrail below closes one of those gaps. ## Guardrail 1: How does a numbered facts list help? A numbered facts list tells ChatGPT exactly what it's allowed to say, and the line above it, "only promise what is here", sets the limit. In the Reply Faster lesson, the facts for a made-up bakery's cake order start like this: ```text Facts (only promise what is here): 1. We can move pickup to Saturday, Oct 3, at 10 a.m. 2. Lemon is fine, same price: $120 total. 3. "Happy 40th, Mike!" on top is fine, no charge. 4. Our lemon recipe has no nuts, but our kitchen also bakes with nuts, so we can't promise any cake is nut-free. ``` The instructions add one more line: "Don't invent details or promise anything that isn't in the facts." Numbering matters too, because it lets you, or ChatGPT, point to "fact 4" later when checking the draft. ## Guardrail 2: What should ChatGPT write when information is missing? Give ChatGPT a fixed phrase for anything it can't find, such as "Not stated", and tell it to use only what you pasted. In the [Summarize a Meeting Transcript](https://learn.ynteractive.com/content/chatgpt-summarize-meeting-transcript) lesson, the request ends: ```text Only use what's in the transcript. If an owner or date isn't said, write "Not stated". ``` In the lesson, two due dates come back as **Not stated**, which is correct: nobody in the meeting said them. You fill them in yourself, because you were there. A blank you can see is far safer than a date that looks real. The same idea works anywhere: "If the email doesn't say, write Unknown" or "If a must-have never came up, write Not discussed." ## Guardrail 3: Where do "never make up" rules go in an AI agent? In an n8n AI agent, put the "never make up" rules in the **System Message**, the standing instruction the agent reads before every request. The [AI Email Responder](https://learn.ynteractive.com/content/ai-email-responder-gmail-drafts-n8n) lesson, built for a made-up pest control company, has a rules section: ```text Rules: You cannot send email. You can only create drafts. If you don't know something, say someone from the team will follow up. Never make up prices, dates or services. ``` The second rule does two jobs: it bans inventing, and it gives the agent something honest to say instead. Without a fallback, a model that's told "don't guess" can still produce an answer that sounds certain. The trade follow-up agents use the same pattern with their own wording. The HVAC agent's prompt says "Do not invent prices, discounts or warranty terms." The electrical agent's says "Do not invent prices, dates, or inspection results. Only use details the user gives you." Name the specific things that would cause trouble in your business if they were made up. ## Try it free, step by step **Reply Faster: Turn a Messy Customer Email Thread into a Clear, Friendly Reply**. Turn a messy customer email thread into a clear, friendly reply: give ChatGPT the thread and your facts, check every promise, fix the tone, and send it from Gmail. You do every step yourself in a practice copy of ChatGPT, it checks your work as you go, and “Do it for me” finishes any step you get stuck on. Free, and nothing touches your real accounts. [Start the free lesson](https://learn.ynteractive.com/modules/chatgpt-reply-faster) [Or read the full step-by-step guide](https://learn.ynteractive.com/content/chatgpt-reply-to-customer-emails) ## Guardrail 4: Why give AI a closed list of choices? A closed list stops the AI from inventing its own categories, and a "Needs Review" option gives it somewhere to put anything that doesn't fit. In the [AI Expense Categorizer Agent](https://learn.ynteractive.com/content/n8n-ai-agent-categorize-business-expenses-google-sheets) lesson, for a made-up bookkeeping firm, the system prompt says: ```text Use only these categories: - Office Supplies - Software & Subscriptions - Meals - Travel - Utilities - Needs Review ``` Then: "If an expense could fit more than one category, or the details are unclear, use Needs Review and say why." And finally: "Do not change amounts or invent details." The escape bucket is what makes the list work. Without it, an unclear expense still has to land somewhere, so the model picks the closest-sounding category and moves on. With it, the unclear ones come to a person. The same pattern fits priorities (Emergency, Same-day, Scheduled), lead ratings and any other sorting job. ## Guardrail 5: How do you catch what slips through? Have a person check the draft against the facts before it goes out, and make ChatGPT help with that check. The Reply Faster lesson uses this prompt after the first draft: ```text Check that reply against my facts. Make a table of every promise or claim in it and the fact that backs it up. Flag anything the facts don't support. ``` In the lesson, the table matches five of six claims to a fact and flags the nut-free line. You ask for a specific fix, then read the final email yourself before clicking **Send**. [Check AI Email Drafts for Promises](https://learn.ynteractive.com/content/blog/check-ai-drafts-for-promises) covers this check in depth, with examples from an insurance agency and a law firm. In n8n, the matching check is to keep the agent's output where a person sees it first. The email responder saves Gmail drafts instead of sending, and the expense agent writes to a sheet that the bookkeeper reviews before anything is posted. ## Do these guardrails make ChatGPT always accurate? No. Guardrails make made-up details much less likely and much easier to catch, but they don't make them impossible. The first draft in the Reply Faster lesson invents the nut-free line even with a facts list and a "don't invent" rule in place. That's why the guardrails work as a set. The facts list and rules prevent most problems, the "Not stated" phrase and the "Needs Review" bucket make gaps visible, and the final check catches the rest. If you're new to writing prompts, [How to Write Better ChatGPT Prompts](https://learn.ynteractive.com/content/blog/write-better-chatgpt-prompts) covers the basics these guardrails build on. ## Key takeaways - ChatGPT fills gaps with likely-sounding text, often called hallucination, so the fix is to leave fewer gaps and make the rest visible. - A numbered facts list with "only promise what is here" limits what an AI reply can say and makes it easy to check. - "If an owner or date isn't said, write 'Not stated'" stops ChatGPT from guessing missing details in summaries and tables. - AI agent system messages should name what must never be made up (prices, dates, services, warranty terms) and give a fallback, like "someone from the team will follow up". - A closed list with a "Needs Review" option, plus a human check before sending, catches what the other guardrails miss. ## Frequently asked questions **Can I stop ChatGPT from hallucinating completely?** No. You can make made-up details rare and easy to spot with a facts list, a "Not stated" rule and clear "never invent" rules, but a person should still check anything that goes to a customer or into your records. **Does telling ChatGPT "don't make things up" work on its own?** It helps, but it works much better with real facts to use and a fallback for missing ones, like "say someone from the team will follow up" or "write Not stated". **Do AI agents in n8n need the same guardrails?** Yes. Put the facts and "never make up" rules in the agent's System Message, use closed lists for sorting, and have the agent save drafts or sheet rows for review instead of sending. **What's the quickest guardrail to start with?** Add "If something isn't in what I pasted, write 'Not stated'" to your next summary request. It takes one line and makes gaps visible right away. ## Free lessons in this post - [Reply Faster: Turn a Messy Customer Email Thread into a Clear, Friendly Reply](https://learn.ynteractive.com/content/chatgpt-reply-to-customer-emails): Turn a messy customer email thread into a clear, friendly reply: give ChatGPT the thread and your facts, check every promise, fix the tone, and send it from Gmail. - [Summarize a Meeting Transcript with ChatGPT](https://learn.ynteractive.com/content/chatgpt-summarize-meeting-transcript): Paste a long meeting transcript into ChatGPT and get the decisions, an action items table with owners and due dates, and a follow-up email ready to send. - [AI Email Responder: Draft Gmail Replies Automatically with n8n](https://learn.ynteractive.com/content/ai-email-responder-gmail-drafts-n8n): Build an n8n agent that watches your Gmail, reads each new customer email, and writes a reply as a draft in the same thread, ready for you to check and send. - [Build an AI Agent That Categorizes Business Expenses](https://learn.ynteractive.com/content/n8n-ai-agent-categorize-business-expenses-google-sheets): Build an AI agent for Maple Street Bookkeeping that sorts business expenses into categories, writes a short note for each and saves them to Google Sheets — chat… ## Related terms Plain-English definitions, each with an example from a free lesson. [Guardrails](https://learn.ynteractive.com/content/glossary/guardrails) · [AI agent](https://learn.ynteractive.com/content/glossary/ai-agent) · [Prompt](https://learn.ynteractive.com/content/glossary/prompt) · [Action](https://learn.ynteractive.com/content/glossary/action) · [Action items](https://learn.ynteractive.com/content/glossary/action-items) · [Agent memory](https://learn.ynteractive.com/content/glossary/agent-memory) · [AI Agent node](https://learn.ynteractive.com/content/glossary/ai-agent-node) · [AI summarization](https://learn.ynteractive.com/content/glossary/ai-summarization) [The full AI glossary](https://learn.ynteractive.com/content/glossary) ## Related prompts - [Action items table prompt](https://learn.ynteractive.com/content/prompts/action-items-table-prompt): Paste a meeting transcript or rough notes and get a table of every task, owner and due date, with "Not stated" wherever nobody… - [AI agent system message prompt](https://learn.ynteractive.com/content/prompts/agent-system-message-draft-prompt): Draft the system message for an n8n AI Agent: who it is, what it knows, its rules and how it writes, including a rule never to… - [Billing question reply prompt](https://learn.ynteractive.com/content/prompts/billing-question-reply-prompt): A ChatGPT prompt for "why was I charged this?" emails: the charge, the correct amount, the reason, the fix as simple math, and… - [Case study draft prompt](https://learn.ynteractive.com/content/prompts/case-study-draft-prompt): Draft a customer case study from your notes, approved results and real quotes. This ChatGPT prompt marks gaps as MISSING instead… [All free prompt templates](https://learn.ynteractive.com/content/prompts) ## Visual guides The same ideas as quick visual guides: swipe through the slides, or read each one as text. - [5 Steps to an AI Agent That Categorizes Business Expenses](https://learn.ynteractive.com/content/visual/5-steps-ai-expense-categorizer): A visual guide: an n8n agent sorts expenses into a fixed list of categories, flags unclear ones as Needs Review and saves them to Google Sheets. - [5 Steps to an AI Email Responder That Only Writes Drafts](https://learn.ynteractive.com/content/visual/5-steps-ai-email-responder-drafts): A visual guide: an n8n agent reads each new Gmail message and saves a reply as a draft in the same thread. You read it and click Send. - [5 Steps to Turn a Messy Email Thread into a Clear Reply](https://learn.ynteractive.com/content/visual/5-steps-reply-to-a-messy-customer-thread): A visual guide: paste a customer thread with numbered facts, check every promise in ChatGPT's draft, fix it and send it from Gmail. [All visual guides](https://learn.ynteractive.com/content/visual) ## Keep reading - [AI Training for Employees: A Free Plan for Small Teams](https://learn.ynteractive.com/content/blog/ai-training-for-employees): AI training for employees on a small-business budget: one rule set, three shared ChatGPT lessons, then role-based picks, all free in practice copies. - [How to Ask ChatGPT for a Table (Prompts That Work)](https://learn.ynteractive.com/content/blog/ask-chatgpt-for-a-table): Ask ChatGPT for a table by naming the columns and saying what goes in an empty cell. Three work prompts: action items, a promise check and a scorecard. - [How to Write Better ChatGPT Prompts: 4 Simple Parts](https://learn.ynteractive.com/content/blog/write-better-chatgpt-prompts): Vague prompts get generic answers full of [Your Company Name]. Role, Context, Task and Format fix that. A real before-and-after, plus a template. [All blog posts](https://learn.ynteractive.com/content/blog) · [All free tutorials](https://learn.ynteractive.com/content)