Hello, I'm Gunnar Hostetler

Healthcare Operations Specialist | LLM Solutions Builder

Two distinct worlds, one driven mindset. I manage high-stakes clinical environments by trade, and architect advanced systems using LLMs to solve the problems I see around me.

View My Work Get In Touch

About Me

I am a Healthcare Operations Specialist driven by intense curiosity. My professional life is defined by the zero-error standards of the operating room. My creative life is defined by a drive to close gaps I see in my daily personal and professional life.

The Open- series is the result of that curiosity. I don't write code in the traditional sense—I leverage the very LLMs I integrate to build the applications themselves. I am the architect and the driver; the model is the engine. I build these tools to solve real problems, and I've found success by simply refusing to accept the status quo.

My Philosophy

  • Privacy by design, not as an afterthought.
  • Technology should solve problems, not create them.
  • The root of complexity is simplicity.
Gunnar Hostetler

Skills & Technologies

iOS Development

Swift SwiftUI Combine Xcode App Store Connect UIKit VisionKit PDFKit MVVM

LLMs & Machine Learning

OpenAI API Anthropic API Pinecone Vector DB RAG Workflows Embeddings LLMs Text Processing Semantic Search

System & Architecture

MVVM Actor Isolation Concurrency Protocol-Oriented System Design Privacy Engineering Secure Storage

Backend & Infrastructure

FastAPI Flask Docker Linux Raspberry Pi MCP Servers WebSockets Async/Await

DevOps & Tools

Git GitHub Actions CI/CD Docker CLI Automation Playwright Zapier

Computer Vision

Vision Framework OCR Image Processing Core ML PDFKit

Healthcare & Operations

Clinical Workflows HIPAA Compliance Medical Device Support Operations Management Technical Training Procurement

Core Strengths

Operational Discipline

My background in high-stakes surgical environments instills a level of rigor and reliability that I demand from the systems I orchestrate.

LLM Orchestration

Architecting complex workflows using LLMs, RAG, and Agents, bridging the gap between raw model capabilities and user needs.

Privacy First

Implementing on-device intelligence and secure storage patterns to ensure user data remains private and protected.

Rapid Iteration

Shipping production-quality code quickly, with a focus on continuous improvement and adapting to the latest platform advancements.

The Open- Series

OpenResponses iOS App Icon

OpenResponses

The successor to my Assistants-era client, rebuilt as a multi-platform OpenAI Responses API playground with AppContainer dependency injection, SwiftUI, and MVVM managing 40+ streaming event types.

  • Model routing: GPT-5, GPT-5 Thinking, GPT-4.1, GPT-4o mini, the o-series reasoning models, and computer-use-preview with cancellable runs, reasoning traces, and per-conversation parameters.
  • Tool coverage: Production-ready Computer Use, Code Interpreter (auto/secure/GPU containers with artifact parsing for 43 file types), File Search across multi-vector stores, Web Search, Image Generation, and custom function schemas.
  • MCP integrations: Ships with official Model Context Protocol connectors for Notion, Gmail, SharePoint, Dropbox, plus remote server templates, all keychain-backed with approval gates.
  • Streaming telemetry: OpenAIService orchestrates 40+ Responses events, surfacing live token counts, tool execution cards, and status chips across iPhone, iPad, Mac (Catalyst), and visionOS.
SwiftUI Combine OpenAI Responses API GPT-5 Model Context Protocol Computer Use MCP Python Sandbox File Search Web Search Async/Await
GitHub
OpenIntelligence

OpenIntelligence

An advanced on-device RAG engine (RAGMLCore) spanning iOS, macOS, and visionOS with SemanticChunker, NLEmbedding, and hybrid retrieval fused through RRF + MMR, all wrapped in a consent-aware SwiftUI interface.

  • Document ingestion: PDFKit + Vision OCR feed SemanticChunker (400-char target, 75-char overlap) before on-device 512-dim embeddings via NLEmbedding.
  • Hybrid retrieval: Reciprocal Rank Fusion combines cosine similarity and BM25 lexical scores, then MMR diversification assembles citations.
  • Service graph: ContainerService, RAGService, HybridSearchService, and PersistentVectorDatabase coordinate ingestion, retrieval, and storage per isolated KnowledgeContainer.
  • Privacy + consent: Cloud calls are blocked until Telemetry-backed consent is granted, with per-provider revocation, Apple PCC routing, and on-device observability.
Apple Intelligence Private Cloud Compute On-Device Analysis SwiftUI Swift 6 RAG On-Device Embeddings LLM Integration Local Storage CloudKit Core ML Hybrid Search Async/Await
GitHub
OpenCone iOS App

OpenCone

A shipped iOS knowledge base that ingests local documents, builds Pinecone serverless indexes, and streams GPT-5 answers backed by the OpenAI Responses API.

  • Processing pipeline: DocumentPicker + security-scoped bookmarks feed PDFKit/Vision OCR, MIME-aware chunking, and text-embedding-3 vectors before Pinecone upserts.
  • Search flow: User queries are embedded, top-k Pinecone matches stream into GPT-5 responses with inline citations.
  • Operational telemetry: DocumentsView + DocumentDetailsView expose timing charts, token counts, and per-step logs for every ingestion.
  • SwiftUI system: MVVM feature modules (Documents, Search, Logs, Settings) share the OCDesignSystem themes, with UserDefaults-backed API settings and roadmaped Keychain migration.
SwiftUI GPT-5 OpenAI Responses API Pinecone API PDFKit Vision OCR RAG Async/Await
App Store GitHub
OpenAssistant iOS App

OpenAssistant

The original Assistants API (v2) client that managed assistants, vector stores, and tool stacks before the Responses API shipped; now maintained as a legacy reference.

  • Assistant lifecycle: CRUD workflows for models, instructions, tool toggles, and deletion built atop async/await + Combine.
  • Vector store tooling: Complete CRUD plus file uploads, chunking strategies, and store-to-assistant linking.
  • File + tool handling: Multipart uploads feed Code Interpreter and File Search with Keychain-backed credential storage.
  • Threaded chat: Markdown-rendered chat UI mirrors OpenAI threads with streaming SSE updates and persistent history.
SwiftUI OpenAI Assistants V2 API (now deprecated) o3-mini / o4-mini Code Interpreter File Search
App Store GitHub

Professional Experience

Independent Builder

Building the Open- Series

Nov 2023 – Present

Leveraging LLMs to build tools. Since my first commit in late 2023, I've used Foundation Models to generate, refine, and ship complex native iOS applications. Driven by a passion for exploration, I orchestrate systems involving RAG, Agents, and on-device intelligence to close the gaps I see in existing software.

  • OpenResponses: Production successor to my Assistants client with Responses API streaming, Computer Use, MCP connectors, and full tool coverage.
  • OpenIntelligence: Privacy-first RAGMLCore engine running on Apple silicon with on-device embeddings, hybrid search, and consent gating.
  • OpenCone: App Store RAG pipeline that pairs Pinecone serverless indexes with GPT-5 answers and detailed ingestion analytics.
  • OpenAssistant: Legacy SwiftUI client covering Assistants, Threads, Runs, and vector stores before the Responses API launched.

OnSite Specialist

Stryker | VA Palo Alto Health Care System

Aug 2022 – Present

Sole technical specialist supporting Stanford surgical teams with complete autonomy. Bridging the gap between complex medical technology and clinical workflows in high-pressure surgical environments.

  • Intraoperative Support: Provide real-time technical support for General, Urology, ENT, and Thoracic surgeries, serving as the subject matter expert for advanced medical devices.
  • Operations & Procurement: Manage end-to-end procurement and inventory for surgical supplies, forecasting needs based on surgical schedules to prevent case delays.
  • Technical Liaison: Act as the primary bridge between surgeons, nursing staff, and biomedical engineering, translating technical constraints into clinical solutions.
  • Compliance & Safety: Maintain strict HIPAA compliance and government clearance (PIV) while managing sensitive case data and equipment protocols.

Get In Touch

Let's Connect

I'm always interested in new opportunities and collaborations, especially in iOS development and AI integration. Feel free to reach out if you'd like to discuss a project, explore potential partnerships, or just say hello!

Gunnarguy@me.com
iOS Engineer | AI Specialist

© 2025 Gunnar Hostetler. All rights reserved.