Bazi Mathangeni

Bazi Mathangeni

AI and Automation Engineer

About

Computer Science Honours graduate with strong expertise in backend development, AI systems, and scalable software architecture. Experienced in building RESTful APIs, ETL pipelines, and cloud‑native applications using Java, C#, Python, and SQL. Skilled in integrating Large Language Models (LLMs) into production systems and deploying containerized applications using Docker and Kubernetes. Passionate about designing intelligent, scalable, and production‑ready software that combines machine learning with modern software engineering practices.

Badges

Tastemaker
Tastemaker

Forums

How to run a customer interview without leading the user

Asking paying customers if they like a new feature usually yields polite nods that mean nothing. During our user research sessions last quarter, I noticed participants would enthusiastically agree with my ideas just to be nice.

The shift happened when I stopped asking hypothetical questions about future features and started asking about their past behavior. Instead of wondering if they would use an automated report builder, I asked when they last built a manual spreadsheet and how long it took.

That specific timeline revealed their actual pain points without biasing their answers with my assumptions. We redesigned the workflow around real bottlenecks, which cut user drop-off by forty percent in the next release cycle.

  • Focus exclusively on what users did last week, not what they plan to do next month.

  • Watch where they hesitate on their current screens instead of listening to their feature requests.

AI more than tripled the code. Releases rose 30%. Usage didn't move. Where's your bottleneck now?

A new study puts numbers on something a lot of us feel: writing code got cheap, and almost nothing after it got any faster. I'd like to hear where the slowdown sits for your team.

I've been reading "Writing Code vs. Shipping Code," an NBER working paper by Mert Demirer (MIT Sloan), Leon Musolff (University of Pennsylvania) and Liyuan Yang. It follows GitHub developers before and after they adopted three generations of AI coding tools: autocomplete, interactive agents that edit alongside you, and autonomous agents that work on their own.

The headline from the revised version on NBER's site (September 2026): cumulative increases in commits of about 30%, 180% and 240% across those three generations. Then the gains shrink at every step down the line. The 240% in commits becomes about 80% more projects and about 30% more actual releases. An earlier May draft had different commit numbers, but the same shape and the same roughly 30% on releases.

The part that stuck with me is the app stores. The authors looked at four marketplaces (Apple's App Store, Google Play, the Chrome Web Store and SourceForge) and found a sharp rise in new apps, but no increase in total usage. More things shipped. People didn't use more things.

View more