News & Innovation
Stay up to date with the latest in technology and innovation
Thanks2Go: Building a Human-Approved Gratitude Rail in One Weekend
I used Codex to its fullest potential as a research partner—for code mapping, source comparison, evidence organization, consistency checks, editorial control, and deliverable preparation. I formulated the intent, defined the scope, interpreted the results, arbitrated the conclusions, and preserved every public decision. This collaboration expands my investigative capacity; judgment, responsibility, authorship, and final signature remain under my authority. This is a submission for Weekend Challe
Building a Secure Personal Gemini Journal with Google Cloud
Most AI apps look impressive in a demo, but building one that is secure, authenticated, and production-ready is a completely different challenge. For my project, I built a Personal Gemini Journal — a private AI-powered journaling application where users can sign in, write their thoughts, chat with Gemini, and get personalized insights from their journal history. 🔐 Security First Instead of starting directly with code, I first configured Google AI Studio with security-focused custom instructions
One Missing Environment Variable Crashed My App in Production (and I Lost My Play Store Testing Streak the Same Night)
#BuildInPublic for the RevenueCat Shipaton 2026. RentDera is my entry, and I'm sharing the whole messy journey in public — wins, crashes, and gut-punches like the one below. This post is part of that trail. The setup Today I shipped v1.1.0 of RentDera, my rent-management app for landlords built with Expo + React Native. It was a big release: Edit properties, units, and tenants after creation Custom & recurring charges on dues Profile pictures Password reset from the login screen Email verifi
What a web proxy has to change before it can register a WebMCP tool
I build TrickyBird, a web proxy, so I'm not neutral here. This is a build note about the part that came before the tool: what we had to switch off first. WebMCP lets a page give the browser's agent a real function instead of a DOM to guess at. You call document.modelContext.registerTool({ name, description, inputSchema, execute }), and the agent can list the tool and call it. The feature sits behind a Permissions Policy whose default is self. On a normal site that default does the isolation for
AI Accountability Coach Agents in 2026: Automate the Between-Session Follow-Up, Then Rent It Out
TL;DR: Accountability is the least glamorous, most valuable part of coaching — and it doesn't scale by hand past a small roster. An AI accountability coach agent closes the gap between sessions: it remembers each client's commitments, checks in on a deliberate cadence in the coach's voice, adapts to the reply, flags at-risk clients, and hands the coach a pre-session digest. This post walks through the architecture of that between-session follow-up loop and makes the 2026 market case for why owni
How senior engineers pass hard technical interviews and land big offers
Two engineers with the same years and the same stack sit the same loop. One gets a mid-level offer, one gets senior with a materially larger package. The gap is rarely knowledge, and it is almost never luck. The level decision is usually made from a handful of moments across the loop, and the same moments come up every time. Once you know which ones they are, they are practisable. None of what follows is about sounding impressive. Most of it is about being more specific than the person interview