# Azure OpenAI Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/azure-openai
> Markdown URL: https://aitinkerers.org/technologies/azure-openai.md
> Technology record last updated: 2026-02-23T03:48:46Z
> Generated: 2026-09-22T17:54:06Z

Deploy OpenAI's leading models (GPT-4, GPT-4o) with Azure's enterprise-grade security, compliance, and scalable infrastructure.

Azure OpenAI Service delivers cutting-edge generative AI: models like GPT-4, GPT-4o, and DALL-E are accessible via secure REST APIs. This is not just a model wrapper; it integrates OpenAI's powerful capabilities with Azure's core enterprise features (data privacy, regional flexibility, Microsoft Entra ID authentication). Organizations confidently scale AI solutions (e.g., customer support automation, code generation) knowing their data remains private and is not used for model training. You get the best of both worlds: advanced AI and a trusted cloud foundation.

- Official technology site: https://azure.microsoft.com/en-us/products/openai-service/
- Public AI Tinkerers demos and talks: 7
- Result page: 1 of 1

## Recent Public Talks and Demos

### [I Let an AI Avatar Introduce Me On Stage.](https://tokyo.aitinkerers.org/talks/rsvp_EAeb_RAMdGM)

I built a browser-based stage controller that made a 3D AI avatar walk on and deliver the opening introduction at the Perxona Tokyo Hackathon on August 8 — instead of introducing myself, I let the avatar do it. It performs a two-minute bilingual monologue with eighteen hand-placed gestures and no repeats, then swaps its face, voice and room live on keyboard cues, and finally lip-syncs to a voice clip my own laptop synthesised offline with no cloud call. It is a single Express server and one vanilla-JS page — no build step, no framework. Live I'll show: the working system, driven by number keys the way it ran on the day. Then the cue script — the gesture tokens and how they resolve at runtime against whichever character is on stage.

- Event context: AI Tinkerers Tokyo - September 1st Meetup — 2026-09-01 — Tokyo
- Public talk page: https://tokyo.aitinkerers.org/talks/rsvp_EAeb_RAMdGM

### [Six Claude Agents and a Trust Boundary: A Clinical Co-Pilot](https://montreal.aitinkerers.org/talks/rsvp_4qzrWmd9MiM)

A multi-agent clinical co-pilot that runs six specialist Claude agents in parallel on top of a PHI-safe pipeline : every LLM call sees only de-identified text, and re-identification happens server-side after the model returns. Live, I'll load a synthetic 68F new-AFib case where the cardiology plan proposes amiodarone for a patient already on warfarin. The Triage, Differential, Pharmacy, Guidelines, Bias-Check, and Communication agents stream into six panels via asyncio.gather. The Pharmacy agent flags the warfarin–amiodarone CYP2C9/3A4 interaction; Bias-Check independently flags anchoring on rhythm control; the orchestrator detects the cross-agent convergence and elevates it as a high-severity flag. I'll then toggle the Safety Gate off so the audience sees raw PHI hit the LLM and get echoed back — then flip it on and show the audit log assertion (zero raw PHI, only counts + SHA-256 hashes). I'll show the FastAPI/WebSocket code that fans out the agents, the trust-boundary diagram, the structured-field redactor, the live audit log tail, and the keystone pytest (test_pharmacy_catches_warfarin_amiodarone). Repo, logs, and 35/35 passing tests are all open.

- Event context: AI Tinkerers Montreal - May Demo Meetup @ Ubisoft — 2026-05-26 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_4qzrWmd9MiM

### [Tenderwise AI-Powered Information Extraction from Tenders](https://bremen.aitinkerers.org/talks/rsvp_8-mQk8tgQIA)

Tenderwise is a web-based Streamlit application that automates the extraction of structured information from unstructured tender documents. It is designed to support procurement, sales, and legal teams by accelerating the analysis of complex tender texts and identifying key requirements, deadlines, and decision-relevant metadata.

- Event context: AI Tinkerers Bremen — 2025-12-10 — Bremen
- Public talk page: https://bremen.aitinkerers.org/talks/rsvp_8-mQk8tgQIA

### [Deploying AI infra at scale using adaptive load balancing](https://sf.aitinkerers.org/talks/rsvp_PD2LQDlDL38)

This session walks through adaptive load balancing for LLM traffic using live code and running services. I’ll open up the Bifrost gateway internals (open source, written in Go) and walk the audience through the request lifecycle: routing, health scoring, concurrency control, quota enforcement, and failover logic. We’ll look directly at: - How the router scores providers and regions based on live latency, error rate, and budget usage. - How per-tenant rate limits and spend controls are enforced without blowing up p95. - How fallback routing and provider failover are implemented so apps keep responding even when one model endpoint degrades. I’ll then run a small cluster, generate load, and intentionally degrade one upstream provider. We’ll watch how traffic shifts in real time, inspect traces in Grafana, and read the routing decisions back from telemetry. Attendees leave with the control loop in Go, the deployment shape (Kubernetes + Postgres + OTEL), and a mental model they can reapply in their own infra.

- Event context: Evals are Over - Evals are Back - AI in Prod @ Okta — 2025-10-31 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_PD2LQDlDL38

### [Unlocking Sensitive Data for AI: Automated Multimodal Anonymization](https://paris.aitinkerers.org/talks/rsvp_9H5tBRLOWtg)

We’ll present Hexagone AI, a platform that automates anonymization across text, images, and audio, making sensitive data safe for AI training, analytics, and sharing while preserving compliance with GDPR and other regulations. The demo will show how our platform anonymizes PDFs in seconds while preserving data utility.

- Event context: Epic Demo night 0.2.1 - Sep 18th, 2025 — 2025-09-18 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_9H5tBRLOWtg

### [Agentic RAG using .NET, Azure AI Search and Semantic Kernel (Part 1)](https://boston.aitinkerers.org/talks/rsvp_x_7FBZozC6Y)

I'm working on improving a RAG application I started last year as a baseline RAG application. The typical semantic search only gets you so far. Now I'm rewriting it to be an agentic RAG application ... and learning a lot along the way. Currently it is .NET and Semanic Kernel.

- Event context: AI Tinkerers Boston June Meetup @ MIT! — 2025-06-30 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_x_7FBZozC6Y

### [Virtual assistant for a tourism company based on AI Agents and RAG](https://medellin.aitinkerers.org/talks/rsvp_rek02Hz6V7Y)

Asistente virtual desarrollado para una empresa de turismo en el que se hace uso de Agentes de IA y RAG. Está conectado a toda la información de la empresa: Hoteles, toures, eventos que organizan, información del staff, información de la empresa y normativas, información de advisors, etc. Toda la arquitectura está basada en servicios de Microsoft, los servicios de speech to text y text to speech son usando los SDK del cognitive service de Azure, los embedding y LLM de AZ OpenAI, la base de datos vectorial del sistema RAG es AI Search, todas las preguntas y respuestas se almacenan en CosmosDB, y está desplegado como una app service en AZ. Trabajé con un enfoque de agentes pero no usando CrewAI u otro framework opensource sino creando mi propio crew de agentes especializados en cada entidad (viajes, staff, eventos, etc) y un orquestador que se encarga de enrutar la pregunta al agente especializado.

- Event context: AI Tinkerers Medellín #3 - Microsoft - 19 de Junio — 2024-06-19 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_rek02Hz6V7Y

## Related Technologies

- [Azure App Service](https://aitinkerers.org/technologies/azure-app-service) ([Markdown](https://aitinkerers.org/technologies/azure-app-service.md)) — 3 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [AGENTS](https://aitinkerers.org/technologies/agents) ([Markdown](https://aitinkerers.org/technologies/agents.md)) — 20 public demos
- [Anthropic](https://aitinkerers.org/technologies/anthropic) ([Markdown](https://aitinkerers.org/technologies/anthropic.md)) — 36 public demos
- [Azure](https://aitinkerers.org/technologies/azure) ([Markdown](https://aitinkerers.org/technologies/azure.md)) — 10 public demos
- [Azure Active Directory](https://aitinkerers.org/technologies/azure-active-directory) ([Markdown](https://aitinkerers.org/technologies/azure-active-directory.md)) — 1 public demo
- [Azure AI Search](https://aitinkerers.org/technologies/azure-ai-search) ([Markdown](https://aitinkerers.org/technologies/azure-ai-search.md)) — 1 public demo
- [Azure Cognitive Search](https://aitinkerers.org/technologies/azure-cognitive-search) ([Markdown](https://aitinkerers.org/technologies/azure-cognitive-search.md)) — 1 public demo
- [Azure Cognitive Services](https://aitinkerers.org/technologies/azure-cognitive-services) ([Markdown](https://aitinkerers.org/technologies/azure-cognitive-services.md)) — 1 public demo
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 216 public demos
- [Cosmos DB](https://aitinkerers.org/technologies/cosmos-db) ([Markdown](https://aitinkerers.org/technologies/cosmos-db.md)) — 1 public demo
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [Express](https://aitinkerers.org/technologies/express) ([Markdown](https://aitinkerers.org/technologies/express.md)) — 18 public demos
- [Go](https://aitinkerers.org/technologies/go) ([Markdown](https://aitinkerers.org/technologies/go.md)) — 25 public demos
- [GPT-4o](https://aitinkerers.org/technologies/gpt-4o) ([Markdown](https://aitinkerers.org/technologies/gpt-4o.md)) — 57 public demos
- [Managed Identities for Azure Resources](https://aitinkerers.org/technologies/managed-identities-for-azure-resources) ([Markdown](https://aitinkerers.org/technologies/managed-identities-for-azure-resources.md)) — 1 public demo
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos