There’s a lot of focus these days on what prompts you can ask Chat GPT, but did you know you can also create a custom GPT? This can be hugely beneficial to businesses wanting to streamline their internal processes and procedures. See how we created a custom peer review GPT as a tool to enhance our in-house processes and output.

Key takeaways

You can build a functional, on-brand peer review GPT in less than 10 minutes if your internal processes are already well documented.

Generative AI will not replace human reviewers, but it can take the first pass and save time across the board.

Formatting and feedback structure are key to GPT usability. Get that right, and you will improve adoption and outcomes.

In-house teams benefit most, but agencies and freelancers can still see strong gains if they build with flexibility in mind.

One GPT might be enough to start, but task-specific GPTs offer better quality and efficiency at scale.

Why I built PRIA, our custom peer review GPT

As a marketing leader with more than 15 years of experience running content teams, I’ve always been a big believer in the power of peer review. It’s how we catch inconsistencies, grow our team’s skills, and maintain quality across everything we create. Then over time, I started to wonder: could generative AI help us do it faster, without cutting corners?

The custom GPT wouldn’t replace our writing team, it would be an experiment to see if a GPT could learn what we’ve been doing for years. This included assessing spelling and grammar, readability, tone, structure, and SEO. Ideally, the tool would deliver those insights in a helpful, structured way with just one click.

Enter PRIA, short for Peer Review Intelligence at Avion. She’s our custom GPT, built specifically to handle the first pass of internal peer review.

What follows is my honest take on how we built her, how it’s going, and what others in similar roles might want to consider before creating their own custom GPT.

Here’s our new friend PRIA. She hangs out in our ChatGPT account waiting to give support when we’d like fresh eyes on a piece of content we’ve written.

Avion’s peer review system

At Avion, peer reviews (PRs) are crucial to producing high-quality client work. Every piece is reviewed by a team member before it goes to our clients. But we’re not just talking about a light proofread.75643

Our peer review system covers six core areas:

Grammar and spelling – Are there any spelling or grammar errors, including region-specific spelling (e.g. UK vs US English)?
Readability – Is the content easy to follow, free of passive voice, repetition, or clunky phrasing?
Tone of voice – Does the copy reflect the intended brand voice and use language appropriately?
Fit for purpose – Does the piece align with the brief and support the intended user journey or business goal?
Structure – Are the ideas logically ordered and clearly presented? Do headings guide the reader effectively?
Metadata and accessibility – Are SEO elements (like headings and metadata) accurate, and is the content accessible (e.g. alt text, inclusive language)?

We track changes in Word, set clear expectations upfront, and encourage constructive and supportive feedback. Our mantra is simple: suggest solutions, not just identify problems.

How to build a custom peer review GPT

This is where you want to start. First, log into ChatGPT and click “GPTs” in your left-hand toolbar. Secondly, click “Create” in the top right corner.

For this to work, I needed to embed PRIA into our way of working. I treated her like a team member with a specific job to do. Like any good assistant she needed a solid brief and clear boundaries.

Using ChatGPT’s custom GPT builder, I uploaded our internal peer review and outlined key instructions. These included how to give feedback, what areas to focus on, and how to structure responses.

The build process itself is straightforward. You’re prompted to describe what you want your GPT to do, what tone to adopt, and which documents or examples to reference. This took less than 10 minutes. Thanks to our existing internal documentation, the first version of PRIA was up and running in no time.

This was a great opportunity for in-house writers embedded with a single client. As established brands these clients already had well-defined guides, documentation, and content strategy frameworks. These documents could be uploaded to shape how the custom GPT worked. I needed to provide additional content every time I used the tool.

This is where you add your guidance – “Create” and “Configure”. The interface is easy to use and doesn’t require any coding knowledge.

Be careful what you feed ChatGPT

ChatGPT seems so knowledgeable because it’s getting all its information from the web. If it’s a book, article, website or other similar source, it’s on the internet and it’s related to the search term or prompt entered by a user, ChatGPT will use it.

We’re more than just mindful about what goes into PRIA. While she’s trained on our internal peer review process, we never upload confidential client work or sensitive information. Where appropriate, we de-identify content first by removing names, brands, and other specifics.

Find out more about how we use generative AI responsibly at Avion.

My pros and cons when it comes to creating a custom GPT

The easy win: building it

PRIA was working almost immediately. That’s largely thanks to our existing peer review documentation, which was already strong. She flagged grammar issues, picked up on repetitive phrasing, and highlighted unclear structures without needing a single custom prompt in the interface.

This whole process took less than 10 minutes! And for most of that time I was playing around with the name.

Manageable: refining her tone

Refining PRIA’s personality and performance was where the real work began. We guided her to be more diplomatic and practical with feedback. For example, one instruction we included was:

Deliver feedback in a constructive and supportive manner. Offer solutions where you see problems. Celebrate what works. Be concise and actionable in your recommendations.

This helped PRIA mirror the tone used by our human reviewers.

The hardest part: formatting feedback

This is where things got tricky: how should PRIA deliver her feedback? What would be most practical for our team?

Here’s our process for formatting feedback:

1. Start with a summary of feedback before diving into specific details

This is what I got back in one click after uploading the first draft of this article into PRIA for a review.

Types of before/after table formats for suggested edits

2. Create different list formats for change recommendations and their rationale

After testing several formats and getting the team’s feedback, we landed on a combination. PRIA provides a short summary, followed by feedback on best practice digital content principles (like SEO, UX and web accessibility) complete with examples This strikes the right balance between depth and speed.

What is “canvas” in ChatGPT?

Canvas is a space in ChatGPT where your GPT can share long-form outputs, side-by-side views, and formatted content like rewrites, tables, and summaries. Think of it as a working space or document editor inside the chat. It’s useful for structured responses like content rewrites, comparison tables, or formatted feedback. And it allows for clearer presentation, which is especially helpful for tasks like peer review where layout and detail matter.

One GPT or many?

Although PRIA started as a generalist peer review assistant, it became clear that task-specific GPTs offer the greatest value.

For one website copy project, I built a bespoke version of PRIA tailored to:

Review alignment with brand messaging
Calculate read time per page
Suggest meta titles and descriptions
Assess CTA strength.

The output was far more relevant because it was focused. This led to a broader realisation: the more specific your GPT’s task, the better the outcome.

Our future plans with custom GPTs

Given the success of creating a custom peer review GPT it makes sense for us to keep the experiment going. After speaking to the team and getting their feedback on the experience I’m wanting to build on what’s already been achieved. Next up, I plan to build additional versions including GPTs for:

Emails that checks subject lines, preheaders, and flow
Social posts that focuses on hooks, engagement, and hashtags
Whitepapers that flags structure, calls to action, and summaries

One general GPT can be useful, but multiple focused GPTs give you real leverage across different content types and can deliver results that are more focused on your query.

Final thoughts: Is creating a custom GPT worth the effort?

If you’re leading an in-house team with clearly defined brand assets, tone of voice, and review standards, it is absolutely worth building your own GPT. You will reduce repetitive tasks, speed up early-stage editing, and maintain consistency with less manual effort.

But if you’re in an agency or freelance environment, the value gained will be different. You’ll need to customise the GPT more often. Even so, using a custom GPT as your first reviewer can reduce time on technical edits and free you up to focus on strategy, creativity, and client relationships.

The key takeaway? Custom GPTs don’t replace quality writing or thoughtful editing, but they do give you a headstart. When you’re juggling deadlines, stakeholders, and multiple projects, that headstart can be a gift.

If you want to know what else you can do with AI, read “Three ways you can take advantage of AI to get more out of your content”.

Image credits: Illustration by pch.vector on Freepik.