Tai
Huynh

I build AI-powered features that ship — RAG pipelines, document intelligence, semantic search, MCP servers.

Every project security-reviewed, tested, and deployable.

11Projects
211Passing tests
100%Security-reviewed
Continue reading
chapters i — iii
Chapter I  ·  Selected Work

A working index
of recent work.

Project / Pitch
I

RAG Chatbot

Upload a PDF, ask questions, get cited streamed answers.

RAGpgvectorstreamingcitations
II

AI Web Scraper

Paste a URL + plain-English fields, get structured data.

Structured extractionSSRF defense
III

Resume Tailor

Paste a job post + your CV, get ATS-aligned rewrites + match score.

Prompt engineeringstructured output
IV

Invoice Extractor

Upload an invoice or receipt, get clean structured data.

Multimodal visiondocument AI
V

FAQ Widget

Drop a script tag, get an AI FAQ assistant on any site.

Embeddable widgetgrounded RAGCORS
VI

Meeting Notes

Paste a transcript, get summary + action items + email.

Long-contextstructured extraction
VII

Semantic Search

Index docs, search by meaning with highlighted snippets.

Embeddingsvector search
VIII

Content Studio

Give a brief, get SEO blog, product, or social copy.

Streaming generationprompt templates
IX

Review Analytics

Paste customer reviews, get sentiment + themes + a report.

Batch classificationaggregationdata-viz
X

NL → SQL

Describe a query in English, get safe read-only SQL.

Code generationSQL safety analysis
XI

Web Research MCP

An MCP server giving any AI assistant safe web access.

MCP protocoltool designSSRF defense
End of selected work — Chapter I.All repositories on GitHub
Chapter II  ·  Method

Built for the real world.

Production-grade isn't a marketing phrase. It means features that can be deployed by someone else's team, survive a security review, and keep running at 3 AM without a phone call.

All 11 projects are security-reviewed and built on a consistent stack so patterns are reusable and integration is predictable.

“Eleven projects · two hundred eleven tests · one stack, one craft.”
— house style
Four operating principles.
01

Ship to production

Every project runs in a real environment with real constraints. No toys, no demos. Auth, rate-limiting, error handling, observability — in by default.

02

Security by default

SSRF defense, prompt injection mitigation, input validation via zod, secrets-free build. Each repo ships with a SECURITY.md — not as an afterthought.

03

Tested and observable

211 passing Vitest tests across the portfolio. Logging and structured errors everywhere. CI runs on every push.

04

One stack, deep craft

Consistent tooling across all 11 projects means transferable context, faster debugging, and a codebase that reads the same way every time.

one toolchain, eleven products
Next.js 14TypeScriptTailwind CSSVertex AI Gemini 2.5 FlashUpstash RediszodVitestCloud RunMCP
Chapter III  ·  Correspondence

Let's build
something.

Available for freelance AI work — RAG, structured extraction, embeddable widgets, MCP servers, internal tools. Typical turnaround 2–7 days.

Email · primaryhuynhchitai.070306@gmail.comSend a messageGitHub · code@huynhchitaiView repositories