The Kryotta blog
Guides and comparisons on working with every AI model — Claude, Gemini, Llama, Mistral, DeepSeek and more — plus what we're building.
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 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.
7 prompt templates for real work: emails, listings, code review and WhatsApp replies
Seven copy-paste prompt templates for emails, product listings, code review, and customer replies. Built for actual work, tested on Claude, Gemini and DeepSeek.
5 myths about AI product videos that waste your Instagram ad budget
Most AI product video myths stem from poor execution, not the technology itself. The real barrier isn't cost or quality—it's knowing what actually works for Instagram ads.
The £0 to £40 AI image and video checklist for product ads: what works and what fails
Test AI visuals for free before spending £40 a month. This checklist shows UK sellers what works in product ads—from choosing the right aspect ratio to writing prompts that actually convert.