The Kryotta blog
Guides and comparisons on working with every AI model — Claude, Gemini, Llama, Mistral, DeepSeek and more — plus what we're building.
I used 4 prompt templates to write 180 eBay listing descriptions: which formula per category
I tested four prompt templates across Claude, Gemini and Llama to write 180 eBay listing descriptions in two weeks. Here's which formula and model worked best for electronics, vintage fashion, collectibles and home goods.
I used 4 prompt templates to write 150 Royal Mail delay emails: which formula per situation
I tested 12 prompt formulas for handling Royal Mail delays and found 4 that work. Here's which template to use for each situation—and why the others failed.
I used 3 AI models to write 80 Cyber Monday email sequences: which one per open rate goal
I tested Claude, Gemini, and GPT on 80 Cyber Monday emails across three segments. One model dominated abandoned-cart recovery. Another crushed VIP messaging. Here's which AI wins for each goal—and why the prompt matters more than the model.
I used 4 AI models to write 100 GDPR data requests in one week: which one per case
I cleared a 103-request GDPR backlog in one week using Claude, Gemini, DeepSeek, and GPT-OSS. Here's which model handled each request type fastest and why it cost only €8.30.
I used 5 prompt templates to write 200 Shopify refund emails: which formula per situation
I handled 200 refund requests in one week using five AI prompt templates. Here's which formula I used for each situation, the exact prompts, and why switching between Claude and Gemini kept my approval rate at 30%.
I made 30 product shots for Takealot with Stability AI during load-shedding: which prompts passed review
I generated 30 product shots with Stability AI during load-shedding to meet a Takealot deadline. Twenty-three passed review. Here's what the prompts needed to work.
I used AI in 5 Nigerian businesses for 60 days: checklist of what worked per industry
I tested AI across five Nigerian business types for two months. Here's what actually saved time and money per industry—and what still needs human judgment.
I made 50 product Reels for Instagram Shop with Luma and Nova: which style got saves
I tested Luma Ray 2, Nova Reel, and Stability's image-to-video on 50 product Reels for my Shopify store. Slow camera moves won on saves—here's what the data showed.
I made 40 product shots for Shopify with Stability AI — which prompts passed and which got refunds
I generated 40 product images with Stability AI for my ceramic shop. Some sold immediately. Others triggered refunds. Here's which prompts customers actually trust.
I used Claude vs Gemini to write 150 GST invoice reminders: which one customers paid faster
I sent 150 overdue GST invoice reminders split between Claude and Gemini to test which AI writes reminders that actually get paid faster. Claude's reminders got paid 40% faster—6.8 days vs 11.4 days.
I used Claude vs Gemini to process 90 Yoco settlement reports during load-shedding
I tested Claude and Gemini to process 90 days of payment settlement reports during Cape Town's load-shedding crisis. Here's which AI model handled interruptions, deduplication, and reconciliation better.
I used Claude vs Gemini to reply to 120 Flutterwave dispute emails: which model won
I tested Claude and Gemini on 120 Flutterwave dispute responses. Claude won 9 out of 11 cases. Here's what separates a winning response from one that gets rejected.