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 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.
I used AI to reply to 200 MTN MoMo payment queries in one week: which model understood cedis
I tested Claude, Gemini and DeepSeek on 200 real payment questions from my Kumasi phone shop during a sale week. Here's which model actually understood cedis and didn't invent refund policies.
I used 3 AI models to review 60 pull requests: checklist for which model per task
I tested Claude, Gemini, and DeepSeek on 60 real pull requests. Each model excelled at different tasks—here's the checklist for which one to use when.
I used AI to reply to 150 Etsy messages during Black Friday: which model kept up
I automated 60% of my Etsy customer messages during Black Friday using AI routing. Here's how I set it up, what failed, and which models actually kept up with 150 messages.
Claude vs Gemini for M-Pesa statement reconciliation: I tested 80 till reports
I tested Claude and Gemini on 80 M-Pesa till statements to see which AI model could cut my three-hour daily reconciliation down. Here's what actually worked.
I made 8 product videos for Flipkart ads with AI — which ones got clicks and which got skipped
I tested three AI video tools on eight Flipkart product ads with a ₹5,000 budget. Four videos hit 4%+ click rates. Four flopped. The difference wasn't the model—it was what I asked it to do.
I made 40 product shots for Flipkart and Meesho with Stability AI: which prompts got clicks
I tested 40 AI-generated product shots across Flipkart and Meesho to find which prompts actually drive clicks. Clean backgrounds won on Flipkart; lifestyle shots dominated on Meesho. Here's the data.
I used 3 AI models to debug a Stripe webhook timeout: which reasoning model found it
A Black Friday payment crisis: orders processed but never delivered. Three AI models tackled the same logs. Only one found the Nginx timeout mismatch killing Shopify API calls.
I used AI to write 50 restaurant menus and WhatsApp order replies — which model kept the Ghanaian English natural
I tested Claude, Gemini, and Llama on 50 real food-stall tasks—writing menus and WhatsApp replies. One kept the warmth and rhythm of Ghanaian English. The others sounded like call centers.
5 myths about AI that waste your money: tokens, hallucinations and context windows explained
You don't pay per question—you pay per token. Context windows aren't memory. And hallucinations aren't lies. Here's what actually costs you money with AI.
I used 3 AI models to review 25 TypeScript pull requests: which one caught the VAT rounding bug
I tested Claude, DeepSeek, and Gemini on 25 TypeScript pull requests. DeepSeek caught a VAT rounding bug that would have cost a client thousands—here's how each model performed.
I made 15 TikTok Shop product videos with AI — which ones got sales and which got scrolled past
I generated 15 AI product videos for my TikTok Shop in two days. Four converted. Here's what worked, what flopped, and why lighting mattered more than motion.