Semantic Kernel Prompts: Complete Guide to All Types with Examples for .NET AI Apps

Sun, 04 May 2025 15:58:12 +0530

Semantic Kernel Prompts: Complete Guide to All Types with Examples for .NET AI Apps

When building AI-native applications with Semantic Kernel, prompts are the instructions you give to an LLM like GPT-4 to generate intelligent responses.

This post is your complete guide to all prompt types in Semantic Kernel — including how to define, use, and invoke them in your .NET app.

🔍 What is a Prompt in Semantic Kernel?

A prompt is a reusable, structured instruction that tells the AI model what to do. Prompts can be used inside:

Plugins (skills)
Agent logic
Planners
Workflows

📦 Types of Prompts in Semantic Kernel

Below are all supported types, with examples:

1. 🧾 Plain Text Prompt

Basic prompts stored inline or in .txt files.

1
2

Summarize this article in one paragraph:
{{$input}}

📂 File: summarize.skprompt.txt 📥 Input passed using the {{$input}} placeholder.

✅ Best for: Simple templated prompts.

2. ⚙️ Semantic Function Prompt (C# Inline)

Prompts defined in C# using CreateFunctionFromPrompt.

var prompt = "Write a professional email reply to:\n{{input}}";
var replyFunc = kernel.CreateFunctionFromPrompt(prompt);

var result = await kernel.InvokeAsync(replyFunc, new() { { "input", "Your shipment is delayed." } });
Console.WriteLine(result.GetValue<string>());

✅ Best for: Quick integration into business logic.

3. 🧠 YAML Prompt Template

Advanced prompts with metadata, inputs, defaults, and model configs.

name: blog_writer
description: Writes a blog post based on a topic
parameters:
  - name: topic
    description: Topic of the blog
    default: "AI and productivity"
template: |
  Write a 3-paragraph blog post about {{topic}}.
execution_settings:
  temperature: 0.7
  max_tokens: 500

✅ Best for: Structured, reusable prompts with input schemas.

4. 🛠️ Prompt with System Role (LLM Behavior Control)

You can set the system role using execution settings.

template: |
  Answer like a financial advisor with short, precise replies.

execution_settings:
  role: system
  temperature: 0.3
  top_p: 0.95

✅ Best for: Controlling model persona or behavior.

5. 🧩 Composite Prompt (Chain Multiple Inputs)

parameters:
  - name: intro
  - name: body
  - name: conclusion
template: |
  {{intro}}

  {{body}}

  {{conclusion}}

execution_settings:
  temperature: 0.6

✅ Best for: Multi-section emails, reports, or formatted outputs.

6. 🔄 Function-Calling Prompt with Plugin Integration

Use a prompt that calls a plugin like MathPlugin.

public class MathPlugin
{
    [KernelFunction("add")]
    [Description("Adds two numbers")]
    public int Add(int a, int b) => a + b;
}

Prompt:

`1`	`What is the result of 7 plus 5?`

The LLM auto-selects add(7, 5) via function calling behind the scenes.

✅ Best for: Allowing LLMs to use your business logic.

7. 🧭 Step Prompt in a Workflow (Process Framework)

Used inside .yaml workflows:

steps:
  - name: ask_topic
    type: prompt
    template: "What topic would you like to write about?"

  - name: write_blog
    type: prompt
    template: "Write a blog post about {{ask_topic}}"

✅ Best for: Guided multi-step user flows and automations.

✅ Pro Tips for Prompt Design

Use clear, task-specific language
Add instructions + examples when possible
Use {{variable}} for flexibility
Lower temperature for consistency; raise it for creativity
Test different wording with real user inputs

📚 Learn More

💬 Got a unique use-case or prompt format you’re working on? Drop it in the comments or tag me — let’s learn together!

If this helped you, don’t forget to ❤️, 🦄, or share it with your .NET AI builder friends!

What is the Process Framework in Semantic Kernel and How It Helps AI App Development

Sat, 03 May 2025 15:58:12 +0530

🧠 What is the Process Framework in Semantic Kernel?

The Process Framework in Semantic Kernel is a high-level orchestration layer that allows developers to define complex AI-driven processes as reusable workflows.

These processes can:

Involve multiple steps or phases
Utilize plugins, agents, prompts, or planners
Support stateful execution and decision logic

Think of it as an AI-native state machine that defines what should happen, when, and how.

Example: You can define a process like Onboard New Employee which involves gathering details, generating a welcome email, and scheduling orientation meetings — all coordinated by the kernel.

🚀 Why Use the Process Framework?

Using the Process Framework gives your AI app superpowers like:

✅ Repeatable AI Workflows

Define repeatable, human-like processes that AI can follow every time a task is triggered.

✅ Declarative Structure

Design your logic in YAML or C#—easy to maintain, version, and update.

✅ Plugin & Planner Integration

Let AI choose when to use a plugin vs. LLM generation vs. planner to solve problems.

✅ Dynamic Decision Making

Incorporate logic, memory, or prompts dynamically based on context or conditions.

📦 Common Use Cases

1. 🧑‍💼 Employee Onboarding Automation

Collect user data
Generate personalized emails
Create calendar invites
Notify HR

2. ✨ Blog Generation Pipeline

Research keyword
Generate blog outline
Write content with SEO focus
Publish to CMS

3. 📄 Document Review Workflow

Analyze uploaded doc
Extract key points
Flag action items
Notify reviewers

🛠️ Example: YAML-Based Process Definition

Here’s a simplified YAML-style structure:

steps:
  - name: collect_input
    type: prompt
    template: "Ask user for project details"

  - name: generate_summary
    type: plugin
    plugin_name: TextSummaryPlugin
    function: summarize

  - name: send_email
    type: plugin
    plugin_name: EmailPlugin
    function: send_email

This defines a flow where:

AI collects input from the user
Uses a plugin to summarize
Sends it using another plugin

🔐 Best Practices

✳️ Start simple: Begin with 2-3 step processes before scaling
🔁 Design for reusability: Make steps generic so they work across scenarios
🧩 Use plugins smartly: Use them to avoid LLM hallucinations on predictable logic
🧠 Add memory: Maintain context between steps with long-term memory

🧠 Final Thoughts

The Process Framework in Semantic Kernel helps developers codify AI behavior with precision, logic, and reuse. It enables building structured flows instead of just ad-hoc prompt chains — making your AI systems smarter, more maintainable, and enterprise-ready.

Whether you’re building internal tools, chatbots, document processors, or content pipelines — Semantic Kernel’s Process Framework brings powerful orchestration to your AI toolkit.

Semantic Kernel C# on The Code Street

Semantic Kernel Prompts: Complete Guide to All Types with Examples for .NET AI Apps

Semantic Kernel Prompts: Complete Guide to All Types with Examples for .NET AI Apps

🔍 What is a Prompt in Semantic Kernel?

📦 Types of Prompts in Semantic Kernel

1. 🧾 Plain Text Prompt

2. ⚙️ Semantic Function Prompt (C# Inline)

3. 🧠 YAML Prompt Template

4. 🛠️ Prompt with System Role (LLM Behavior Control)

5. 🧩 Composite Prompt (Chain Multiple Inputs)

6. 🔄 Function-Calling Prompt with Plugin Integration

7. 🧭 Step Prompt in a Workflow (Process Framework)

✅ Pro Tips for Prompt Design

📚 Learn More

What is the Process Framework in Semantic Kernel and How It Helps AI App Development

🧠 What is the Process Framework in Semantic Kernel?

🚀 Why Use the Process Framework?

✅ Repeatable AI Workflows

✅ Declarative Structure

✅ Plugin & Planner Integration

✅ Dynamic Decision Making

📦 Common Use Cases

1. 🧑‍💼 Employee Onboarding Automation

2. ✨ Blog Generation Pipeline

3. 📄 Document Review Workflow

🛠️ Example: YAML-Based Process Definition

🔐 Best Practices

🧠 Final Thoughts