about
one of my colleagues encouraged me to share my experiments and learnings in a blog. i told him there are thousands of them! i know they are exist because i learn all what i know from the internet. i said if i am going to create a blogpost on a topic it would be the 1001st content on it. he told me that i was right but why still not?
and that is how 1001 was born. a blog about building production grade software with ai. i will be sharing insights, experiments, and learnings from my journey with the tools i use every day, like claude code and codex, and the patterns that actually work when you let an ai agent do the heavy work.
no hype, no product reviews. just what i learn from shipping real code with these tools. what works, what breaks, and how to think about it.
topics
- spec-driven development · write a clear spec before you prompt. better input, better output.
- agentic loops · how agents plan, run, and repeat. this is at the heart of how these tools get work done.
- multi-agent orchestration · running several agents together. one writes, one reviews, one tests.
- planning & execution · how models break down tasks, pick tools, and follow through.
- claude code & codex · using these tools every day. what i set up, how i use them, and where they work well or not.
- code review with ai · checking what agents write. when to trust the output and when to question it.
- context engineering · what the model sees matters more than what you ask. how to shape repos and context for better results.
- mcp & tool use · giving agents access to real systems through the model context protocol.
- testing with ai · letting agents write and run tests. making sure the code they produce actually works.