Your function documentation is the new API for AI. Learn how to build agents that can discover and correctly use your code.
#1about 5 minutes
Controlling PowerShell with natural language commands
A live demo shows how a large language model can translate human language into executable PowerShell commands to manage system processes.
#2about 4 minutes
How large language models process text using tokens
Models break down text into numerical tokens for efficient processing, which is a fundamental concept for performance and cost calculation.
#3about 8 minutes
Calculating semantic similarity with embeddings and vectors
Text is converted into numerical vectors (embeddings) to calculate semantic similarity using cosine similarity, enabling features like recommendations and search.
#4about 5 minutes
How completion models generate text probabilistically
LLMs generate text by probabilistically selecting the next token, and the temperature parameter controls the creativity versus determinism of the output.
#5about 3 minutes
Implementing function calling with Semantic Kernel agents
An AI agent uses embeddings to understand user intent and trigger the correct external function or plugin from a library of available tools.
Related jobs
Jobs that call for the skills explored in this talk.
With AIs wide open - WeAreDevelopers at All Things Open 2025Last week our VP of Developer Relations, Chris Heilmann, flew to Raleigh, North Carolina to present at All Things Open . An excellent event he had spoken at a few times in the past and this being the “Lucky 13” edition, he didn’t hesitate to come and...
Stephan Gillich - Bringing AI EverywhereIn the ever-evolving world of technology, AI continues to be the frontier for innovation and transformation. Stephan Gillich, from the AI Center of Excellence at Intel, dove into the subject in a recent session titled "Bringing AI Everywhere," sheddi...
24:24
25:17
23:33
57:52
29:54
32:55
28:38
26:35
