Our “Jennifer” GPT grader keeps our writers honest. She grades ruthlessly, counts specifics, and enforces the blog posting guidelines that make our content sound like us, not like ChatGPT.
But because of OpenAI’s current sharing restrictions, only our team can access Jennifer directly. So in this guide, we’ll teach you how to build your own version from scratch, complete with grading logic, structure, and penalties.
Start With the Job Description
Before you write a single line of instruction, define the role.
Jennifer is a strict grader. That’s her entire job.
Give your GPT a clear, single-purpose identity, something like:
Name: “001 Jennifer – Article Grader”
Description: “Strict grader using clear, concise writing standards and content guidelines.”
That clarity tells the model how to think before it ever touches an article.
Build the Rubric
Most people write vague prompts like “Check for clarity and SEO.”
That’s amateur hour. A strong grader needs quantifiable rules.
Here’s the core of Jennifer’s rubric, you can copy and tweak it:
| Rule | Penalty | Why |
|---|---|---|
| Fewer than 10 specific examples (names, places, quotes) | -1 letter grade | Real stories = trust |
| Fewer than 3 internal links to your own content | -1 letter grade | Builds EEAT & SEO |
| Salesy or “fluffy” tone | Max grade = C | Readers trust authenticity |
| Each typo or grammar error | -1 letter grade | Quality is non-negotiable |
| ChatGPT giveaways (“doesn’t just do X, it also does Y”) | -1 letter grade | Sounds robotic |
| Overly long or vague writing | -1 letter grade | Brevity = clarity |
This converts subjective editing into objective math.
When your writers complain about grades, you can show them the receipts.
Write the System Instructions Like a Real Manager
Open the “Configure” screen of your custom GPT and paste your rubric as strict instructions.
Example core block (trimmed from our own):
Grade harshly. An A must be at the level of world-class journalism from a national
publication.
Less than 10% of submissions should earn an A.
Make sure the article fits the audience and topic of the site.
If a personal brand site, include relationship context (people, places, experiences).
If fewer than 10 specifics, drop a full letter.
If fewer than 3 internal links, drop a full letter.
Sales tone = C max.
Every typo = -1 letter.
If writing is unclear or wordy, -1 letter.
List counts of specifics and links in feedback.
That’s it. Short, strict, measurable.
Add Your Knowledge Files
Upload blog posting guidelines and Content Factory Workbook (or whatever your content bible is).
This gives the GPT context for your tone, linking habits, and structure.
Jennifer references this file automatically, which is why her feedback feels “on-brand” instead of generic.
Preload Smart Conversation Starters
These help your team use the GPT correctly without having to explain the rules each time.
Here are ours (and you should copy them verbatim):
- “Grade this blog post from a team member on becoming Googleable.”
- “Review this article for ChatGPT-like language.”
- “Does this article meet our EEAT standards?”
- “Is this post good enough to repurpose for localservicespotlight.com?”
These act like ready-made prompts that keep grading consistent.
Ban the “AI Giveaways”
Make your grader allergic to robotic writing.
We explicitly flag and penalize phrases like:
- “In conclusion”
- “Moreover / Furthermore / Nonetheless”
- “X doesn’t just do Y; it’s also Z.”
- “As a leading provider…”
- “Cutting-edge solutions…”
- “Holistic approach…”
Whenever Jennifer finds one, she automatically drops the grade.
How to Clone Jennifer for Your Own Team
You can’t copy our exact GPT (OpenAI restricts sharing), but you can replicate her brain in minutes.
1. Go to chat.openai.com → Explore GPTs → Create.
2. Hit Configure.
3. Name your GPT and set Description.
4. Paste your rubric into Instructions.
5. Upload your house style or content guideline PDF.
6. Add conversation starters (optional but recommended).
7. Save.
That’s it. You’ve got your own Jennifer; your own custom editor that won’t sugarcoat anything.
Final Thought
AI tools don’t replace editors; they enforce standards at scale.
Jennifer is our strictest team member, never sleeps, and never gets tired of telling writers their work is “a solid C.”
And that’s exactly why our content keeps improving.
Dennis Yu
Dennis Yu is the CEO of Local Service Spotlight, a platform that amplifies the reputations of contractors and local service businesses using the Content Factory process. He is a former search engine engineer who has spent a billion dollars on Google and Facebook ads for Nike, Quiznos, Ashley Furniture, Red Bull, State Farm, and other brands.
Dennis has achieved 25% of his goal of creating a million digital marketing jobs by partnering with universities, professional organizations, and agencies. Through Local Service Spotlight, he teaches the Dollar a Day strategy and Content Factory training to help local service businesses enhance their existing local reputation and make the phone ring.
Dennis coaches young adult agency owners serving plumbers, AC technicians, landscapers, roofers, electricians, and believes there should be a standard in measuring local marketing efforts, much like doctors and plumbers must be certified.