amananuworks@gmail.com

I’m Amanbuilding thoughtful systems.

Products · AI · moving images

Kochi, India · Available worldwide

Selected work

Building in public

A live log of work in motion.

Experiments, systems, and repos moving forward.

github.com/amxcodes
Account
@amxcodes
Contributions
—
Active days
—
Window
6 months

Live public activity

Move across the graph
Loading GitHub activity

A few notes

What I’m drawn to.

I move between product thinking, code, and moving images. The small details are usually where the feeling begins.

A cobalt-blue line drawing of Aman Anu in profile, with three handwritten annotations.

Experience

  1. At , I work as a - owning , , , and .

  2. Earlier, with , I supported .

Education

  1. I completed a at , building a base in , , and .

Notes in progress

A few things I’m working through.

Products, images, systems, and the details between them.

AI, creativity, software engineering, creative process

The Difference Between Iteration and Exploration

AI makes it easier than ever to reach a convincing result. But refining an idea is not the same as exploring whether it was the right idea in the first place. The distinction matters in creative work and software engineering alike.
Open note 7 min read · Oct 2026

An engineering essay about Rust rewrites, AI-assisted coding, memory safety, verification, and resource-efficient software.

The Return to Performance-Optimized Software

As AI makes code cheaper to generate, developers are reconsidering the cost of running, verifying, and maintaining it. From Rust rewrites and memory safety to lightweight AI agents and local-first applications, this essay explores why software efficiency may be becoming a competitive advantage again.
Open note 12 min read · Oct 2026

The Problem With Being Able to Build Anything

AI lowers the cost of trying an idea. The harder work is deciding which idea deserves it, designing for the consequences, and knowing when to stop.
Open note 19 min read · Oct 2026

Writing · AI Systems · Technical Analysis · 6 min read

Claude’s newest feature? A secret handshake

Anthropic recently announced machine-readable watermarking for Claude text outputs to meet EU AI Act obligations. Here is what is publicly confirmed, what remains unknown, and how LLM text watermarking actually works under the hood.
Open note 8 min read · Aug 2026

Essay · Personal Reflection · Building

The Myth of the Readymade Path: Why Failure Is Still the Only Real Way In

Internet advice promises clean blueprints, but true understanding requires stumbling through the architecture yourself.
Open note 5 min read · Aug 2026

AI Engineering · Framework Design · Software Architecture

Designing Frameworks for Model Co-Authorship

An exploration of how modern software frameworks, developer tooling, and protocols are adapting to optimize for artificial intelligence code assistance.
Open note 7 min read · Aug 2026