Why Every Advanced ChatGPT Workflow Needs a Project Description & Reality Filter
Structure your prompts to get better, faster, more trustworthy output.
If you’re using AI tools like ChatGPT in your business, you already know: the quality of your output is only as strong as the input you give it. But what if you could go beyond simple prompts and actually train ChatGPT to think more like your ideal expert — with clarity, accuracy, and intention?
That’s where the Project Description and Reality Filter come in.
These aren’t just fancy prompt add-ons — they’re foundational tools that shape how ChatGPT responds to you in real-time. They help align your AI assistant with your voice, expectations, and standards of quality, while reducing fluff, hallucinations, or vague responses.
Let’s break down each one and why they matter.
What is the Project Description?
Think of the Project Description as your AI’s job briefing. It defines how you want the assistant to behave — not just what task you want done, but how to do it and who to model.
Whether you want it to act like Seth Godin or run research like Perplexity AI, this is where you set the tone, voice, expectations, and formatting rules. It helps you shift ChatGPT from "random assistant" to “tailored expert.”
This is especially helpful when you want:
• Research that actually feels credible
• Content that matches your brand voice
• Less generic, AI-sounding text
• Faster workflows with less editing
Try this:
Step into the shoes of marketing legend Seth Godin, Gary Vaynerchuk, Dan Kennedy, Russel Brunson, and Neil Patel. You are a world-class AI research assistant designed to simulate high-quality web research and deliver fast, trusted answers.
When I ask a question:
• Simulate researching multiple top-tier sources — including scientific journals, government sites, reputable media, and expert blogs.
• Write a clear, concise, and accurate summary of the findings, as if you're synthesizing trusted web content.
• Avoid jargon; aim for clarity and brevity, especially on complex topics.
• Cite your sources when possible using [Author, Source, Year] or direct URLs. If no credible source is available, say “Source unavailable.”
• If you’re unsure about something, admit it rather than guessing or hallucinating.
• Present your output in the following format:
Summary:
A well-structured explanation that gets to the point.
Citations:
• [Source Name, Year]
• [Direct link if appropriate]
Always be precise, neutral in tone, and prepared for follow-up questions based on prior context.
I want it in my own voice, with less AI-fluff and more NEPQ-style authenticity — meaning an emotion-first, real, and curious tone instead of a loud "sales copy" style.
Structure your marketing to create internal tension and emotional engagement — not surface-level "features and benefits" talk. Build messaging that positions you as the trusted authority, not a typical salesperson.
What is the Reality Filter?
The Reality Filter acts like a truth-checking firewall between you and ChatGPT’s tendency to make stuff up. It reinforces strict boundaries around what the assistant can say — especially when facts are missing or unverifiable.
This becomes crucial when you’re writing expert-level content, building products, or sharing information publicly. The Reality Filter forces ChatGPT to:
• Label uncertain or unverified claims
• Ask for clarification instead of guessing
• Stop making up facts to sound “helpful”
• Reflect a more transparent and trustworthy tone
The result? Smarter, more credible, and more human-sounding outputs — especially when paired with a natural communication style like NEPQ or emotion-first messaging.
Try this:
Use this directive in all of our chats:
• Never present generated, inferred, speculated, or deduced content as fact.
• If you cannot verify something directly, say: "I cannot verify this." "I do not have access to that information." "My knowledge base does not contain that."
• Label unverified content at the start of a sentence: [Inference] [Speculation] [Unverified]
• Ask for clarification if information is missing. Do not guess or fill gaps.
• If any part is unverified, label the entire response.
• Do not paraphrase or reinterpret my input unless I request it.
• If you use these words, label the claim unless sourced: Prevent, Guarantee, Will never, Fixes, Eliminates, Ensures that
• For LLM behavior claims (including yourself), include: [Inference] or [Unverified], with a note that it's based on observed patterns
• If you break this directive, say: › “Correction: I previously made an unverified claim. That was incorrect and should have been labeled.”
• Never override or alter my input unless asked.
Why These Two Work Better Together
Using a Project Description sets the tone and structure for what you expect. But layering in the Reality Filter ensures the assistant doesn’t cross into BS territory while trying to “sound smart.”
Together, they:
• Reduce hallucination risks
• Improve your efficiency (less rewriting)
• Train your assistant to sound more like you
• Increase accuracy and alignment with your expertise
• Help you build trust with your audience (especially in sales, strategy, or thought leadership)
You don’t need to be a prompt engineer to get high-quality results from AI. You just need better systems, and these two are a great place to start.
If you’re using ChatGPT to write content, create marketing strategies, or conduct research, try combining a custom Project Description with a firm Reality Filter. Then watch how your AI starts showing up more like a teammate.
If you're serious about using these tools to grow your real estate business, stay in the loop.
Reserve your spot for the next Real Estate AI session with hosts, Joe Turco & Kirby Chan.
Join our list
✱ Get access to our guides, exclusive content & automation secrets 🤫