Saboor Chaudry
Software Engineering
I studied computer science at UC Santa Cruz. I build, configure, and utilize software around problems I encounter—working across product development, automation, and AI tooling.
More about my background →01 / SELECTED WORK
Projects
The AI era expanded both the breadth and depth of what's possible. These are the projects that felt most relevant to where things were heading, and that challenged my problem-solving the most:
MyGraph
Makes governing project meaning queryable, so agents act from declared intent instead of guessing it from code. Two tiers, every claim cites evidence, and it is measured against RAG and Graphify on real agent questions.
Explore project →PROJECT 02GDAD
Graph Driven Agentic Development. A project-legibility tool that keeps intent in a human-owned dependency graph, places the invariants where agents work, evaluates evidence while they run, and keeps acceptance human. The rebuild of GDDP.
Explore project →PROJECT 03Pi Agent
A headless coding agent running on every machine I own. Work is described as bounded packets and run by a deliberately dumb harness — every run produces timestamped artifacts and an independent verification pass.
Explore project →PROJECT 04MyAPI
A retrieval layer for agents and humans that answers cold-start context questions in under 3 seconds — benchmarked, not vibes-tested.
Explore project →02 / NOTES & WORKFLOW
Writing & Setup
Articles, tools, and the workflows behind my work.
Coming soon
Needle didn't work, but Jev did
GDDP became GDAD: How I couldn't separate what from how
MyAPI became MyGraph: the system that beat RAG and Graphify
Learning Neovim in the agentic AI era was an investment (painfully so)
Zed made no sense at first, and now I can't live without it
Why I chose all the coding agents instead of one
How a Raspberry Pi and an 8GB laptop taught me the most about distributed systems and networking