Skip to content
View yorzi's full-sized avatar
๐Ÿ 
Working from home
๐Ÿ 
Working from home

Block or report yorzi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please donโ€™t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
yorzi/README.md

Hello World ๐Ÿ‘‹

Senior Rails & AI Product Engineer โ€” Production AI Workflows & End-to-End Delivery

I'm Andy Wang, a senior Rails & AI Product Engineer based in Xi'an, China (UTC+8).
Building web software since 2005, primarily Ruby on Rails since 2008, working remotely with US and European teams since 2011.

My work is the product system around model capabilities โ€” multi-stage workflows, application state, retries, human review, evaluation and observability โ€” rather than one-off prompts or demos.

๐Ÿ”ญ What I'm working on

  • HexagramCast โ€” creator and primary builder. A traceable I Ching reflection tool: 8 casting methods (4 traditional, 4 deterministic modern), with the input digest, computation trace, moving lines and classical source layers all inspectable. No fortune-telling, no luck scores. English-first, also in ็ฎ€ไฝ“ไธญๆ–‡ and ็น้ซ”ไธญๆ–‡; web, API and browser-extension entry points.

๐Ÿ› ๏ธ What I build well

  • Rails product systems โ€” greenfield builds and mature codebases I own over the long term
  • Complex business workflows โ€” payments and subscriptions, lesson/resource scheduling, marketplaces, CMS and multi-channel publishing, data and reporting, admin and operational tooling
  • Multi-party platforms โ€” roles, documents, agreements and state machines, including private-investment onboarding workflows, health-device data portals and vendor marketplaces
  • Production AI workflows โ€” structured inputs and outputs, asynchronous state, retries and failure recovery, human review, evaluation, cost control and observability
  • Legacy modernization โ€” Rails upgrades, test suites, background processing and third-party integrations

๐Ÿ’ฌ Reach out

I'm most useful where a product has real users, non-trivial workflows, and a codebase that has to keep working while it changes. Happy to talk about senior AI product engineering, Rails systems, production AI workflow integration, and end-to-end product delivery.

๐Ÿ’ผ LinkedIn ใƒป๐ŸŒ Website

Pinned Loading

  1. shakacode/react_on_rails shakacode/react_on_rails Public

    Integration of React + Webpack + Rails including server-side rendering of React, enabling a better developer experience and faster client performance.

    Ruby 5.2k 629

  2. patterns-ai-core/langchainrb patterns-ai-core/langchainrb Public

    Build LLM-powered applications in Ruby

    Ruby 2k 263

  3. acts_as_favable acts_as_favable Public

    Allows for favorite refer to be added to multiple and different models.

    Ruby 53 9

  4. NUARIG/surveyor NUARIG/surveyor Public

    A Rails gem that lets you code surveys, questionnaires, quizzes, etc... and add them to your app.

    Ruby 752 271