iOS App

Butler.ai

iOS app that uses LLM sampling and reasoning to intelligently schedule your day. Protects deep work, respects constraints.

SwiftLLM SamplingiOS
This Site

theojiang.dev

Zero frameworks, static HTML/CSS/JS. Served by Caddy with automatic HTTPS via Let's Encrypt. Hosted on DigitalOcean NYC1.

HTMLCSSCaddyDigitalOcean
// Approach
How I think about systems
01

Ship, then optimize

Make it work, make it correct, make it fast. In that order. A running system that generates data is worth more than a perfect system that's never deployed.

02

Let systems learn

Every trade, every rejection, every market regime shift is training data. Build feedback loops that turn failures into calibration, not just log entries.

03

Adversarial by default

Good ideas survive scrutiny. Every proposal gets a bull case, a bear case, and a risk review before it touches real capital. Confirmation bias is the enemy.

04

Automate the boring

Humans should make judgment calls, not babysit cron jobs. If a machine can do it reliably at 3 AM, it shouldn't require a human at 9 AM.

// Stack
What I work with

Languages

GoC# / .NETPythonJavaRustTypeScript

Auth & Security

OAuth 2.0/2.1OIDCmTLSAzure Entra IDAWS IAM

AI & LLM

MCP ProtocolRAG PipelinesSemantic SearchOpenAIClaude APIEmbeddings

Infrastructure

KubernetesDockerHelmCI/CDGrafanaPrometheusgRPC

Cloud

Azure AKSAWS EC2/ECS/LambdaS3CDKLoad Balancers

Data

PostgreSQLMySQLCosmos DBDynamoDBRedis
// Contact
Let's connect
Open to interesting conversations about Agent platforms & Auth, MCP, or new opportunities.
GitHub@TTTheo
LinkedInzehuijiang
Email[email protected]