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 AI models to write 180 Cyber Monday SMS campaigns: which one per open rate
A freelancer tested four AI models on 180 SMS campaigns across six D2C brands. Here's which model won for storytelling, urgency, brevity, and price-led copy—and the open rates that proved it.
I used Claude vs Gemini to write 100 Klarna dispute responses: which one per claim
I tested Claude and Gemini on 103 real Klarna disputes from my outdoor gear shop. Claude won overall, but each model dominated different claim types—here's which one to use for what.
I used 4 AI models to write 200 Stripe dispute responses: which one won per claim type
I tested Claude, Gemini, GPT, and DeepSeek on 200 real Stripe disputes across fraud claims, chargebacks, and subscription cancellations. Here's which model won per category and why.
I used Claude vs Gemini to write 120 eBay return policy pages: which one reduced disputes
I rewrote 120 eBay return policies using Claude and Gemini to see which AI model actually reduced buyer disputes. The results weren't what the forums predicted.
I used 3 AI models to write 120 Black Friday email sequences: which one per open rate
I tested Claude, Gemini, and GPT-OSS writing 120 Black Friday email sequences for my Shopify store. Here's which model won on open rates—and why the difference actually mattered.
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 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 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 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.
Claude vs Gemini for Yoco and SnapScan payment reconciliation: I tested 70 reports
I tested Claude and Gemini on 70 real payment reports from my Cape Town coffee roastery. Here's which AI catches duplicate transactions, handles Afrikaans notes, and actually explains discrepancies to non-technical staff.
Claude vs Gemini for VAT returns: I tested 50 B2C invoices and refund credits
I tested Claude Sonnet 4.5 and Gemini Pro on 50 real VAT invoices—UK sales, Irish cross-border, and refund credits. Here's which model handles each scenario correctly, and why format matters as much as math.
I used AI to reply to 180 Jumia return requests in one week: which model understood the refund policy
I tested Claude, Gemini and DeepSeek to auto-draft replies to 180 return requests after a clearance sale. Here's which model best understood Jumia's refund policy and customer frustration.