AI engineer building agents, AI products, and the software around them.

Open to AI engineering and full-stack rolesChiang Mai · --:-- GMT+7

Today

I take products from idea to production: from the first prototype to the deploy that customers use. Right now I’m building AI products for client work, and on the side experimenting with agents, developer tools, and small software businesses of my own. Tools change; shipping does not.

What I do

AI products

Built end to end and shipped.

Agent systems

Retrieval, tools, and evals that keep agents honest.

Full-stack engineering

The interface, API, and data around the model.

Cloud & infrastructure

Terraform, containers, AWS and Azure.

Projects

Let’s Hear ItmacOS

A native macOS app for reading and listening to English EPUBs and text-based PDFs. Narration runs locally on your Mac.

A multi-tenant platform for building AI agents and deploying them to web, voice, and messaging. Lead engineer at DasomX.

An AI learning platform that generates courses and narrated videos from source material. Lead engineer at DasomX.

Writing

AI is an amplifier, not an equalizer

Every company has the same coding agents. The output is not the same. AI multiplies what you already bring, and it multiplies the gap with it.

The brain gets better at what you actually do

Neuroplasticity is real, but it is narrow and it fades. What that means for how I learn new tools, and for what I let an agent do for me.

Your agent should never see the key

Credentials belong outside the sandbox. I compare five agent runtimes and the gap between containment and delegated authority.

Elsewhere

Code on GitHub, thoughts on X, and the longer story on LinkedIn. For work, write to hello@briansithu.com.