zabirauf || Zohaib

The goal wasn't to build something useful.

I feel there is spectrum between vibe coding and agentic engineering, which I like to refer to as Outcome Driven Development (ODD).

I’ve been primarily using Claude Code.

Good article describing CRI (Color Rendering Index).

Coding agents have a tendency to make all experiences be alike.

I've been thinking about AI-generated tests and the friction around them.

I've been building webtomarkdown.com to have a tool that allows me to convert various type of content to Markdown so I can pass it to LLMs (Markdown is the language of LLMs).

DeepSeek-R1 has created quite a stir in the AI world, with headlines all over the place, primarily focusing on the low cost aspects of it to create a competitive model that butts head with o1 reasoning models from OpenAI.

I transitioned to the role of Engineering Manager approximately 5 years ago, since then I haven't been programming in my day job but the itch to do so has always been there.

When setting up a NixOS system, we often want to store secrets in environment variables for various tools to use.

Ollama is a powerful and user friendly tool for running and managing large language models (LLMs) locally.

OpenWebUI is a self-hosted UI for interacting with various LLM models, both on-device and in the cloud.

Professionally I've been working in Outlook Copilot and building experiences to leverage the LLMs in the email flow.

With the recent advances in Large Language Models and a lot of the innovation happening in regards to that in Python, it's becoming more advantageous to use Python not only for research purpose but also for building products that end users will use.

In this post I'll go over on approach for onboarding new early hires remotely that I've formed from my experience.