Build Log & Field Notes
Documenting the engineering journey: what worked, architectural failures, prompt evaluation benchmarks, and reflections on building independent digital products.
Engineering Smart AI Cashflow Tracker: From Receipt Chaos to Predictive Runway
Why backward-looking budgeting apps fail, how we built local-first receipt intelligence, and lessons from launching on Google Play.
Most expense trackers fail because manual data entry is exhausting and backwards-looking charts don't tell you if you'll run out of money in 3 weeks. Here is how we engineered an offline-first AI cashflow companion for Android.
How I Built an AI Assistant for Italian Driving Theory
What problem I discovered, how I engineered the explanation vector loop, and lessons from 5,000+ quizzes.
When studying for the Italian Patente B exam, candidates don't just struggle with traffic rules—they get tripped up by linguistic traps and legal phrasing. Here is how I turned ministerial exams into an intelligent AI tutor.
Why We Should Build AI Assistants, Not Just Chatbots
The fundamental difference between open-ended conversational interfaces and high-leverage workflows.
A blank chat box puts all the cognitive burden on the user. True AI assistants embed intelligence directly where decisions happen.
The Anatomy of an Autonomous Research Agent
Moving from single-shot prompting to self-correcting agent loops with LangGraph and critic verifiers.
How we designed ResearchPulse AI to decompose complex research questions, execute parallel browser queries, and verify facts before writing reports.
Why Every Independent Builder Needs a Lab Mindset
How framing your work as experiments unlocks speed, eliminates perfectionism, and accelerates shipping.
Not every idea has to be a venture-backed startup. The Lab philosophy gives you permission to test bold ideas, document failures, and ship constantly.