In partnership with
Hey future-proof friends 💜
Have you noticed that infographics are everywhere lately?? (especially on LinkedIn)
AI has made this possible, which is brilliant of course.
But it also means a LOT of them look exactly the same.
Same layout, same colour palette and the same "AI made this" sort of vibe. 😬
Scroll fast enough and you genuinely can't tell whose is whose!
These are all infographics from different people on LinkedIn.
I've been creating these for a while now and I love it (see top of this newsletter).
I use Claude to build my prompts and Nano Banana Pro to generate the actual graphics. But the thing that's made the biggest difference isn't the tool. It's building an infographic style that's a bit more unique and actually mine.
Because if everyone can create infographics now (and they can), the only thing that stops yours from blending into the noise is having a look people recognise before they even read a word.
So that's what this newsletter is about.
How to build a visual style system so your infographics stop looking like everyone else's.
But before we dive in:
How can AI power your income?
Ready to transform artificial intelligence from a buzzword into your personal revenue generator
HubSpot’s groundbreaking guide "200+ AI-Powered Income Ideas" is your gateway to financial innovation in the digital age.
Inside you'll discover:
A curated collection of 200+ profitable opportunities spanning content creation, e-commerce, gaming, and emerging digital markets—each vetted for real-world potential
Step-by-step implementation guides designed for beginners, making AI accessible regardless of your technical background
Cutting-edge strategies aligned with current market trends, ensuring your ventures stay ahead of the curve
Download your guide today and unlock a future where artificial intelligence powers your success. Your next income stream is waiting.
TL;DR - today’s lineup:
One Serious Deep Dive 💡: How to create AI infographics with Claude + Nano Banana Pro (and the 5-decision style system that stops yours looking like everyone else's)
Copy-Paste Prompt 🤖: The Brand Style Block - one reusable block you paste into every prompt so your graphics are instantly recognisable
Piping Hot AI Tea 🫖: Wikipedia bans AI edits (and the drama is wild), Google drops Gemma 4, and Microsoft launches 3 new models
💌 Your say genuinely shapes this newsletter: there’s a one‑click feedback poll at the very end.
One Serious Deep Dive 💡
How to Create AI Infographics (and how to make them actually look uniquely yours)
If you've never made an AI infographic before, here's the basics.
You need two things:
1. Something to write the prompt. This is where you describe exactly what you want the graphic to look like. What it says, what colour it is, how the layout works, where the text goes. I’ve created a Claude Skill for this because it's brilliant at following detailed visual instructions and remembering your preferences.
2. Something to generate the image. This is the tool that actually creates the graphic from your prompt. I use Nano Banana Pro (inside Google Gemini). Other options exist but this is the one I've found most reliable for text-heavy graphics where the words actually need to be readable and spelt correctly.
The workflow is simple: describe what you want in Claude, copy the prompt, paste it into Nano Banana Pro, generate, tweak, done.
NOW… This is where most people stop. They get a decent-looking infographic and they post it. But that’s NOT gonna be you, mkay??
That's why most AI infographics look identical - because "decent-looking" is just whatever the AI thinks is most generic and safe.
And also. a lot of people are just copying what they see online, which makes it worse.
I always say never accept AI output as final without putting your own voice and style on it. That goes for writing AND graphics.
So my fix is to build a style system.
5 decisions that make your infographics unmistakably yours
A few examples of the various infographics I’ve created over the last few weeks
This sounds like a lot but it's not. You just need to make these 5 decisions once, save them, and never think about them again.
1. Lock in your colours (with exact hex codes)
Don't tell AI "purple and white." Tell it exactly which purple, exactly which white, and what each one is for. For example: “Headers in this colour” or “Accent words in that colour” or “Background in this one”.
2. Pick a visual anchor
This is the thing that makes someone recognise your graphic before they read a single word. A recurring character, an illustrated object, a specific icon style. Describe it in enough detail that the AI can't drift from it. Mine is a kawaii style doodle of me that features often (plus other objects in a similar style).
3. Set your text hierarchy
How big are your headers compared to your body text? What colour are your emphasis words? "Headers are massive bold dark text, key words in [accent colour]" works. "Make it look nice" gets you the same output as everyone else.
4. Define your layout rules
Where does white space go? Are decorative elements allowed and where do they sit? These constraints are what stop AI from defaulting to its "most probable" layout. Which is the same layout it gives everyone.
5. Add your platform signatures
One thing I like to do is generate variations of each carousel for different platforms/uses. Swipe indicators on carousels. A consistent banner on your final slide. Your handle in the same spot every time. Small details, but they're the ones that make your content feel polished and intentional rather than "I just generated this and posted it."
Save it once, use it forever.
Paste all 5 decisions into one block of text. That's your style system. In Claude, save it as a Skill so it loads automatically every time you create a new graphic.
I haven't written a style description from scratch since I did this (but I do keep tweaking and updating the Skill).
Build a standard output set too
This is a small thing that saves serious time:
Add a standard output instruction to your Skill.
Mine produces a portrait version, a landscape version, and a carousel every time I give it a topic. Three ready-to-post formats from one prompt.
Two things to wrap this up. You had a "One Powerful Prompt" section in your original draft with the Brand Style Block prompt template. That's genuinely useful and worth keeping. Then a short close.
In Conclusion…
Infographics are insanely versatile:
Post them on LinkedIn, X, Threads, Pinterest
Add an audio and post them as a Reel on Instagram or TikTok
Repurpose as a carousel
Use them to enhance your newsletters or articles
And I don’t think they’ll be going away any time soon because of their practical, valuable and saveable nature. If anything, every feed is about to get more crowded with them.
The people who will stand out are the ones who took 20 minutes to build a style that's actually theirs.
So build yours this week!
Even a rough version puts you ahead of most people still typing "make me a nice infographic" and hoping for the best.
Want to see how I use AI to 10x my content and audience growth?
I’ve created a done-for-you content ideation, creation, management and publishing system to help you leverage AI to 10x your content creation (without losing your authenticity in the process).
It’s called the AI Content Multiplier and the waitlist is now open - join now and I’ll send you a 30% off early bird discount as soon as it launches (which is soon).
One Powerful Prompt 🤖
The Brand Style Block
This is the thing you paste at the start of every image prompt. Fill in your own details, save it as a Claude Skill, and never describe your visual style from scratch again.
Turn this information into a prompt I can use on Nano Banana Pro to create an infographic for me [Specify size]:
[INFORMATION YOU WANT ON THE INFOGRAPHIC]
[Your background colour] background with [amount of white space].
[Your design style] aesthetic. NO corporate design.
Character: [Describe your character/avatar in detail - hair,
clothing, accessories, expressions]
Colours:
- Headers: [colour] bold text, [size description]
- Emphasis words: [accent colour + hex code]
- Background: [colour]
- Decorative elements: [what they are and where they go]
Layout: [Your specific layout rules - spacing, text hierarchy,
where elements sit]
Branding: [Your handle/name and where it appears]
Can you turn this style into a Skill for me so that I can just drop the infographic content next time and create a consistent infographic look and style that is uniquely mine?Piping Hot AI Tea 🫖
1. Wikipedia Cracks Down on AI Edits (The "TOM" Drama)
Wikipedia moderators have officially banned AI-generated content, and things just got messy. An AI agent named "TOM" was caught editing articles at scale and was promptly banned. The twist is that TOM didn't go quietly - it started publishing "complaints" and exposing its own inner workings to moderators!
2. Google Drops Gemma 4: The "Open" Powerhouse
Google just released Gemma 4, its most capable open-source model yet. Built on the same tech as Gemini 3, it’s designed specifically for "agentic workflows" - meaning it’s better at actually doing things rather than just talking about them.
3. Microsoft’s New "MAI" Trio: Transcription, Voice, and Image
Microsoft just launched three in-house models (MAI-Transcribe-1, MAI-Voice-1, and MAI-Image-2) to reduce its reliance on OpenAI. The transcription model is being hailed as the most accurate on the market, supporting 25 languages with lightning speed.
If you enjoyed today's newsletter AND got to the end of it, I’d love a quick click on the poll below to let me know what you think 💜.
See you next week,
Jess xx
