CH·01 / Open-source agent
Preflight
An AI agent that fills job applications, with dry runs enforced inside the browser.
805 tests · CI on Linux + macOS
Blake Bailey
Automation & AI agent engineer
I build AI agents that do real work safely, and the tests that prove it.
Featured work
CH·02 / Browser game
Lantern Hollow
A small, cozy dungeon crawler that runs in the browser, built with plain JavaScript and Canvas 2D.
CH·03 / Earlier work
Earlier work
Learning projects from 2020: Node.js APIs, real-time chat, React front ends and a full-stack store.
- Weather-Website
- Task-Manager-API
- chat-app
- eCommerce-Site
- Markdown-Previewer
- Random-Quote-Machine
- Drum-Machine
CH·04 / About
About
I build AI agents and the automation around them, and I like knowing exactly how a system works before I trust it. Away from the keyboard I race motorcycles and coach riders.
- Based in
- Florence, SC
- Work
- Open to remote roles in the US
- Hardware
- Built a local inference server (4× RTX 6000 Pro)
CH·05 / Writing
Writing
- Enforcing an AI agent's dry run inside the browser
Why a prompt that says "don't submit" is not enough, and the guard, hook and audit that make Preflight's dry runs hold.
- Testing an agent that must never submit
How Preflight's test suite proves its dry-run guard works, with a fake LLM, real Chromium and requests that never arrive.
CH·06 / Contact
Get in touch
- Emailblake@blakells.dev
- GitHubgithub.com/Blakells