This talk was recorded at NDC AI in Oslo, Norway. 
#ndcai #ndcconferences #developer #softwaredeveloper    

Attend the next NDC conference near you: 
https://ndcconferences.com
https://ndc-ai.com/

Subscribe to our YouTube channel and learn every day:   
/       @NDC 

Follow our Social Media!

https://www.facebook.com/ndcconferences
https://twitter.com/NDC_Conferences
https://www.instagram.com/ndc_conferences/

#ai #openai #code #llm 

Agentic AI enables large language models to use tools to interact beyond system boundaries. From no-code implementations in Copilot Studio to developing sophisticated solutions using LangChain and Semantic Kernel, developers of all levels can leverage tools to create agentic solutions.

But how does agentic AI work under the hood?
How are models able to understand when to use a tool and how to use it?

In this demo intensive session Alan will explain the concepts of agentic AI in detail. Starting with the basics of function calling in the Open AI models, he will cover the techniques used to provide tools to models, and how the models are able to understand and use the tools. The use of prompting to guide models and improve tool call behavior will be covered, along with guidelines for adding tools to your solution. Alan will also cover the protocols used by Open AI models as well as how the model context protocol is used to provide compatibility between services and LLM solutions.

Join this session if you want to understand what goes on under the hood of function calling, MCP and agentic AI.

NDC Conferences

A conference talk (NDC AI 2026) exploring how AI agents work under the hood, focusing on function calling, Model Context Protocol (MCP), and tool use. The speaker demonstrates how LLMs infer which tools to call based on tool definitions and system prompts — without directly executing the tools themselves. Live demos cover a pizza ordering agent, agentic RAG with Wikipedia, a vibe-coding copilot, and an MCP-based DJ server. Key topics include non-determinism in tool selection, token management in RAG, the distinction between function calling and MCP, security risks (tool trust, credit card data leakage, malicious MCP servers), and how to customize GitHub Copilot with skills and instructions.

AI Agents In-Depth – Function Calling, MCP and Tool Use Under the Hood - Alan Smith - NDC AI 2026