Boran Oktay D.

AI automation engineer for operating businesses. I build AI agents and internal AI tools that take real work off your team, connected to the CRM, databases and apps you already use, in Python with Claude, Claude Code and MCP servers. $260,000 earned on Upwork across 125 completed projects, 5,229 hours billed, 100% Job Success Score, Top Rated Plus. Most AI work dies in the gap between a demo that works and a process that works on a Monday morning. Closing that gap is the whole job. Clients I have built for include Trukkin (logistics), Bells of Steel (ecommerce), LGFG Fashion House (fashion), Ultrassure (insurance), Genvision (climate tech), Bowery Boost (performance marketing), Moor Marketing (lead generation) and Ta3swim (ecommerce). My most recent closed contract ran 2,051 hours and ended with a 5 star review. Istanbul, UTC+3. I overlap 09:00 to 13:00 US Eastern every weekday and answer inside 4 hours outside that window. You work with me directly. I write the code myself. WHAT I DO AI Consulting and AI Implementation An AI audit of how your business actually runs: where AI pays for itself, where it does not, and a roadmap in the order it should be built. Then I implement it, so the plan does not die in a slide deck. Many of my clients keep me on as a fractional AI engineer after the first build, which is why most of my contracts run for months, not days. AI Agent Development and Internal AI Tools Single and multi-agent large language model (LLM) systems that take real actions, not just answer questions: LangGraph and LangChain orchestration, AI model integration with the Claude API and OpenAI API, Model Context Protocol (MCP) servers that connect Claude to your own data and tools, function calling, and human approval gates wherever a mistake is expensive. Internal tools built around one company's process, for operations, sales and support teams. Claude Code and Claude Cowork setups, documented so your team can keep using them. AI Automation and System Integration Business process automation, CRM automation and automated workflow design across the tools your team already uses. Two way syncs between systems that were never designed to talk to each other. APIs, webhooks, and the payload changes that quietly break things overnight. ZOHO CRM, email, databases and data flows across your stack, with Python orchestration first. Fixing and Hardening What You Already Have A workflow that ran for months and then stopped. An agent that answers confidently and is wrong. A prototype with the API keys sitting in a file. I diagnose it, fix it, and leave it running: logging, error handling, retries, version control, permissions. Three of my active contracts are improving and extending systems that were already in production, including a weekly ML agents program running since February 2025. RAG and AI Chatbot Development Retrieval augmented generation that stays accurate as the document set grows, with source citations so any answer can be checked. Chunking, embeddings, natural language processing, Pinecone, ChromaDB, GraphRAG and evaluation. Support and sales chatbots grounded in your own documents, with escalation to a human when confidence is low. Data Pipelines and AI App Development Large scale web scraping, ETL, cleaning and enrichment. End to end AI development of generative AI products when the product itself is the goal: Python and FastAPI backends, authentication, billing, dashboards, cloud deployment. RESULTS BY INDUSTRY Real Estate: 30+ automation projects (Zillow, CoStar), AI powered house price calculators, ZOHO CRM integrations. Digital Marketing: AI SEO researchers, content generators, YouTube analytics agents, full blog production pipelines. Healthcare and SaaS: AI chatbots, personalized email systems, lead generation platforms taken from zero to live products. Sales and Go to Market: AI sales agents, lead research and qualification, outreach personalization at scale. TECH STACK Artificial Intelligence: Claude, Claude Code, Claude API, OpenAI GPT, Gemini, MCP servers, AI agents, LLM agent development, multi-agent architectures, LangChain, LangGraph, function calling, prompt engineering, evaluation and guardrails RAG and Data: RAG pipelines, GraphRAG, embeddings, vector databases, Pinecone, ChromaDB, PostgreSQL, ETL, large scale scraping Backend: Python, FastAPI, Node.js, REST APIs, webhooks, Docker Automation and Integration: API integration, business process automation, CRM automation, ZOHO CRM, workflow automation Cloud: AWS, GCP, Azure HOW I WORK I ask about the business before I write code. I tell you when something should not be automated. I document what I build in plain English, so your team can own it after I am gone. Send me the process you want covered and I will tell you what it can own, what stays with your team, and how long it takes.