Building a bilingual AI chatbot for Canadian users: English, French and the privacy checks in the code
A chatbot that works well for a shop in Dallas can still go wrong in Toronto, Montreal or Ottawa....
Tag archive
A chatbot that works well for a shop in Dallas can still go wrong in Toronto, Montreal or Ottawa....
A long time ago, in So, you want to vibecode an other note taking app? (Part 1), I promised to follow...
A small support team answers the same questions every day: prices, hours, cancellations. Each answer...
Two stacks, one decision: text vs real-time audio, and what each really costs to run.

Five things I learned building a streaming local LLM chatbot in about 100 lines of Python, with real benchmark numbers from an M1 Pro.

Most small businesses do not lose customers because their product is bad. They lose them because...
By Jonald Penpillo, AI developer and software engineer in General Santos City, Philippines. Most...
Three types of AI receptionist, what each niche needs, five things it must never do and six questions to ask before you pay.
App store screenshots all look the same: a beautiful portrait, a witty opening line, a promise of...

A support chatbot starts giving wrong answers the moment it’s allowed to guess. Ground it in approved...
How to Select a Chatbot API for Invoice Quality Tradeoffs — Portable Cost Analysis Short...
Getting a language model to answer WhatsApp messages takes an afternoon. Getting it to stop answering...