At its core, Semantic Kernel is a framework built around LLMs by Microsoft. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more.

The core idea of the library is that we can “PLAN” the chain of thoughts around steps to accomplish the goal to create more advanced use cases around LLMs.

Prompt templates:
Prompt templates are templates for different types of prompts. Like “chatbot” style templates, etc

Planner:
The concept of planning the execution of thought process to reach a goal or an acceptable outcome

LLMs:
Large language models like GPT-4o, Claude, Grok 2, LLAMA, GEMINI, etc

Agents:
Agents use LLMs to decide what actions should be taken. Tools like web search or calculators can be used, and all are packaged into a logical loop of operations.

Memory:
Short-term memory, long-term memory.

We will dive into each of these in much more detail in this session.

You will learn:

• Understanding of Microsoft Semantic Kernel fundamentals
• Applying Semantic Kernel in real life examples orchestrating chats with an LLM
• Planning, executing and generating a flow to reach a desired outcome using Semantic Kernel