Spencer Schneidenbach
AI Architect, Microsoft MVP, President/CTO Aviron Labs
St. Louis, Missouri, United States
Actions
Spencer Schneidenbach is an AI Architect, President, and CTO of Aviron Labs, an AI and software development firm based in the United States. He has been recognized as a Microsoft MVP for his AI expertise and contributions to the community. Visit our website at https://avironlabs.com for more information.
Links
Badges
Area of Expertise
Topics
You Don't Need Python: Building Production AI Systems in the Language You Already Know
Have you jumped fully onto the AI hype train yet? Maybe you’re a developer who’s dipped their toes into the AI waters with ChatGPT or you’ve built a small proof-of-concept using OpenAI’s API.
Imagine giving your applications knowledge on how to easily call functions in your own code depending on the given task. If your software booked reservations for restaurants, imagine how awesome it would be to teach ChatGPT how to book those reservations – with only a few lines of code.
Join Spencer as we explore how the AI products of the world (including Vercel's AI SDK, Agent Framework, and others) can integrate your applications with AI services like ChatGPT. We’ll discuss how these libraries can help teach your AIs how to invoke your own code using plugins, how to teach AIs to optimize code calling, and how you can leverage retrieval-augmented generation (RAG) to further enhance AI’s context around your application’s data.
Threat Modeling for AI Agents: From Prompt Injection to Tool Abuse to Data Exfiltration
AI agents are everywhere now - from coding assistants that can access your entire codebase to customer service bots that can book flights and process refunds. But while we're racing to give LLMs more capabilities, have we stopped to consider the security implications? When your AI can execute code, query databases, and make API calls on behalf of users, the attack surface isn't just bigger - it's fundamentally different.
In this session, we break down the real security risks of AI-enabled applications, from prompt injection attacks that can hijack your agent's tools to data exfiltration through seemingly innocent queries. We'll explore how attackers exploit LLM vulnerabilities, demonstrate practical defensive strategies, and discuss securing tool calls, implementing proper authorization boundaries for agentic systems, and building robust validation layers between your LLM and your critical systems.
By the end of this talk, you'll understand the unique security challenges of AI-powered applications and walk away with a practical framework for threat modeling and securing your LLM integrations. Whether you're building your first AI agent or already running LLMs in production, you'll gain the knowledge to keep your AI-enabled systems secure without sacrificing their power.
Production RAG Beyond the Tutorial: Agentic Retrieval That Actually Works at Scale
Everyone can build a RAG pipeline that works on a demo. Embed some docs, run a cosine similarity search, stuff the results into a prompt - done, right? Then you deploy it to production and discover your retrieval is surfacing irrelevant documents, missing obvious matches, and hallucinating sources your users trusted.
In this session, Spencer will share from-the-trenches case studies from production RAG systems handling real business data at scale. We'll go over why naive embedding search fails, how strategies like hybrid retrieval (full-text + semantic) dramatically improves relevance, and the chunking and re-ranking strategies that actually matter. You'll also learn how to measure whether your retrieval is actually working, because if you're not measuring, you're guessing.
This isn't another "RAG 101" talk - it's the talk you need after your first RAG pipeline disappoints you.
Introducing N#: What I Learned Building a .NET Language Entirely with AI
What's the most ambitious thing you can vibe-code? Spencer decided to find out by building N# - a working .NET programming language, complete with compiler, tooling, and language server support - entirely with AI coding agents.
In this session, Spencer will take you through the full journey: from initial language design prompts to a functioning compiler that targets .NET. We'll go over how to structure truly ambitious AI-assisted projects, when to let the AI run vs. when to take the wheel, and what breaks when you push these tools to their absolute limits.
This isn't just a flex - it's the most extreme stress-test of AI coding tools you'll ever see, and every lesson transfers to your own projects.
Arming Your AI Agent: MCP, RAG, Skills, and the Extensibility Stack
Every capability you give your AI agent can make it even better, but different tools have different strengths and weaknesses. Between RAG, MCP, tools, skills, CLIs, and APIs, how do you know which one to choose?
In this session, Spencer will break down the extensibility architecture that makes production AI agents actually useful. We'll go over how MCP gives you the connection layer to external systems, RAG gives you the knowledge layer for domain-specific retrieval, and skills give you the behavior layer for complex multi-step workflows - and more importantly, how to compose them in real production systems. We'll cover the practical decisions: when to use MCP vs. direct tool calls, when RAG beats stuffing context into the prompt, when you should go basic and shell out to a CLI, and how to test all of it.
Come with an AI agent that can answer questions. Leave knowing how to make it actually do things.
LLMs/AI and the .NET tooling landscape
Have you jumped fully onto the AI hype train yet? Maybe you’re a developer who’s dipped their toes into the AI waters with ChatGPT or you’ve built a small proof-of-concept using OpenAI’s API.
Imagine giving your applications knowledge on how to easily call functions in your own code depending on the given task. If your software booked reservations for restaurants, imagine how awesome it would be to teach ChatGPT how to book those reservations – with only a few lines of code.
Join Spencer as we explore how Microsoft’s AI products (including Agent Framework) can integrate your applications with AI services like ChatGPT. We’ll discuss how these libraries can help teach your AIs how to invoke your own code using plugins, how to teach AIs to optimize code calling, and how you can leverage retrieval-augmented generation (RAG) to further enhance AI’s context around your application’s data.
The Business Value of Agentic AI - A Real World Case Study
Curious about a real-world implementation of AI looks like? Have your dipped your toes in the deep AI waters but need some ideas on how to let the (AI) rubber meet the (business) road?
In this session, Spencer will break down a project where he was put in charge of integrating Azure OpenAI into an application. We’ll discuss how he leveraged Microsoft’s Semantic Kernel to rapidly iterate and give the LLM access to data within the target system, how he used prompt engineering and retrieval-augmented generation (RAG) to enhance the efficacy of the AI’s responses, and how he cost-optimized the LLM as the project went on, reducing the costs from the initial deployment by 10 times.
Come to this jam-packed session and get the lessons learned from integrating AI in a real world setting as well as an in-depth overview of the tools involved.
Coding While You Sleep: How I Deliver Real, Paid Projects Running AI Agents Overnight
AI coding tools like Claude Code and OpenAI Codex are powerful amplifiers of existing developer skill. But exactly how far can you take them? Is Ralph really a useful way to write software?
Spencer ran AI agents overnight, letting them tackle complex problems while he slept, for both paid projects (that netted over USD$250k in revenue!) as well as some fun side projects - and he's been doing it long before Ralph was cool.
In this session, Spencer will share the lessons he learned from pushing AI coding agents to their limits. We'll discuss how to structure prompts and tasks for long-running agent sessions, how to set up your projects so agents can work autonomously, and how to review and validate AI-generated code so you're not shipping garbage. We'll also cover the practical, everyday techniques that make you a more effective AI-assisted developer.
If you've been curious about Ralphing but haven't figured out how to make Ralph truly productive, this session will give you a roadmap. Come ready to learn how to put AI agents to work - even while you're off the clock.
KCDC 2025 Sessionize Event
dev up 2025 Sessionize Event
Nebraska.Code() 2025 Sessionize Event
SDD 2025 Sessionize Event
Memphis Global AI Community Bootcamp Sessionize Event
STL TechWeek 2025 Sessionize Event
Global AI Bootcamp - Saint Louis Sessionize Event
Update Conference Prague 2024 Sessionize Event
dev up 2024 Sessionize Event
Beer City Code 2024 Sessionize Event
KCDC 2024 Sessionize Event
DevConf 2023 Sessionize Event
dev up 2023 Sessionize Event
NDC London 2023 Sessionize Event
CodeMash 2023 Sessionize Event
Update Conference Prague 2022 Sessionize Event
KCDC 2022 Sessionize Event
dev up 2022 Sessionize Event
NDC Oslo 2021 Sessionize Event
KCDC 2021 Sessionize Event
Update Now 2020 Sessionize Event
NDC London 2020 Sessionize Event
KCDC 2019 Sessionize Event
NDC Oslo 2019 Sessionize Event
NDC Minnesota 2019 Sessionize Event
NDC Porto 2019 Sessionize Event
KCDC 2018 Sessionize Event
NDC Oslo 2018 Sessionize Event
NDC Minnesota 2018 Sessionize Event
NDC London 2018 Sessionize Event
Spencer Schneidenbach
AI Architect, Microsoft MVP, President/CTO Aviron Labs
St. Louis, Missouri, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top