Skip to content
View huseyinkaplandev's full-sized avatar
馃幆
Focusing
馃幆
Focusing

Organizations

@Revotas

Block or report huseyinkaplandev

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 don鈥檛 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 user鈥檚 behavior. Learn more about reporting abuse.

Report abuse
huseyinkaplandev/README.md

Huseyin Kaplan

AI-Native Full-Stack Engineer 路 RAG & Evaluation Systems 路 TypeScript/Node.js + Python

I build full-stack products and bounded AI reference systems with TypeScript, React/Next.js, Node.js, Python, and PostgreSQL. Based in Istanbul.

Selected work

Live deterministic TypeScript support operations console with cited responses, structured action proposals, human approval gates, and an explicitly synthetic evaluation dashboard.

Live demo

One agent policy implemented twice, as a hand-written tool-calling loop and as a LangGraph state graph, benchmarked against a deterministic model across three scenarios. Identical behaviour, 94% more code for the graph. Turborepo, TypeScript, benchmark enforced as a CI gate.

Live demo

Public deterministic LLM reliability and evaluation harness covering citation checks, expected-fact coverage, abstention, latency, and estimated cost.

Live demo

Deterministic RAG and evaluation reference implementation with citations, abstention, offline evaluation, tests, Docker, and CI. It is not a production customer system.

Live demo

Tedavio AI

Founder-built clinic AI MVP with bounded product and reliability workflows.

Stack

  • TypeScript, React, Next.js, Node.js
  • Python, PostgreSQL, Supabase
  • Docker, GitHub Actions, Playwright, Vercel

Contact

PortfolioLinkedInEmail

Pinned Loading

  1. production-rag-evals production-rag-evals Public

    Hybrid RAG reference with RRF, citations, abstention, offline evals, FastAPI, Docker, and CI.

    Python

  2. ai-support-ops-console ai-support-ops-console Public

    Deterministic AI support operations console with cited streaming, approval gates, synthetic evals, and CI

    TypeScript

  3. llm-reliability-lab llm-reliability-lab Public

    Deterministic evals for citations, grounding, abstention, latency and LLM cost

    Python

  4. agent-runtime-bench agent-runtime-bench Public

    Native tool-calling loop vs LangGraph state graph: same policy, deterministic model, measured side by side.

    TypeScript