Ideas, analysis, and updates from the Kanha team.
A step-by-step guide: from sign-up to a production chatbot trained on your site.
Retrieval misses, per-query costs, and why fine-tuning beats reading comprehension for support bots.
When inference runs in the browser, there's nothing to log, nothing to leak, nothing to comply with.
The math behind per-query pricing, and how to escape it.