For the last few weeks, I have been shipping blogs, code, and videos as part of a FREE and self-published course called Understanding Semantic Kernel.   The course is spread over 7 parts.   I am pleased to announce that it’s now complete.   It covers the fundamentals of the open-source SDK from Microsoft.   In this course, you will learn how to use key components that form the SDK and how to create an agentic AI solution that can be embedded within an ASP.NET Core web application.   By the end of the course, you will understand: what Semantic Kernel can do how to create integrations with popular LLMs such as GPT-4 how to integrate the OpenAI Completions endpoint. how to augment existing software application with new AI capabilities   The course is delivered using detailed blogs, code, and video content to aid your learning of this up-and-coming technology. ~ Deep Dive Written Content and Code The course consists of the following parts:   (Part

In an earlier blog post, we saw how to implement Native Functions and Plugins using Semantic Kernel. A Native Function was contained within the Plugin and was invoked directly. This isn’t how you’d normally use a Native Function.  If you wanted to invoke code directly, you’d create a regular class with a deterministic method and execute it. When augmenting applications with AI capabilities using Semantic Kernel and language model, the Planner component in Semantic Kernel decides which Native Function to use. Under the hood, the Planner makes use of Function Calling. In this blog post we will learn about Function Calling and Planners. Specifically, the following will be covered: What is Function Calling How Does Function Calling Work What is a Planner How Planners Use Function Calling   A code walkthrough, examples, and video demo are included.  The video demo shows you how to create a customer service agent that can handle a variety of tasks. ~ What is Function Calling Functio

In the previous blog post, we saw how to create and run prompt functions inline. These were effectively hardcoded. In most situations, you will likely want some more flexibility or to be able to share prompt function definitions across different or multiple projects. In this blog post you will see how prompt definitions can be loaded from the file-system and used within Semantic Kernel. What is a File-Based Prompt Function? Loading function prompts from the file system lets you specify the definition of function prompt in a flat file. At the time of writing, two flavours of file-based function prompts exist: .txt and paired .json file single YAML file   The function prompt definition from either option is then serialised by the Semantic Kernel runtime then used as part of the interaction with the human and machine / LLM. Important to note that YAML definition is supported by Azure AI Studio. I think that, over time, this will end up becoming the standard.  It’s early days however and we

In the previous blog post, I introduced Semantic Kernel, the components that form the open source SDK, and how it can be used in conjunction to with Open AI to create a simple conversational agent. In this blog post, I take a closer look at how you can leverage prompts to create Inline Prompt Functions when using Semantic Kernel. The following is covered: Inline prompt functions Ensuring predictability Refining LLM prompt output Few-shot prompting Handling unexpected user input   Templatising and calling loading prompt functions from the file system are not included.  These capabilities will be covered in a future blog post. ~ What Is a Prompt? A prompt is the initial input given to a language model to produce a specific response. This input can be a simple query or a complex directive, to guide the AI's output.  Crafting effective prompts is essential for optimizing AI performance and ensuring accurate, contextually relevant responses. A common task for people that interact w

What Is Semantic Kernel? Semantic Kernel had been on my radar for a while. Semantic Kernel is an open-source SDK designed to simplify the creation of agents that can interface with your existing code. The SDK is extensible and supports models from OpenAI, Azure OpenAI, Hugging Face, and more. Using the SDK means you don't have to learn the inner workings of LLM provider APIs. Semantic Kernel lets you build agents using C#, Python or Java.  Complex workflows and agentic AI orchestrations can be created using C#, Python or Java. With the open-source SDK from Microsoft recently reaching V1, now is the time to dig into what this can do. ~ Orchestration Layer Semantic Kernel sits at the centre of the agent stack.  It acts as the main orchestration layer for your agentic AI solution. AI models, and plugins (your existing code) can be easily integrated to help you create innovative solutions and user experiences. (image source Microsoft) In the past, this involved manually stitching together mul

In May I built a private journal and mood tracking prototype that ran on JSON files.   I decided to adapt this and publish this as an online micro-SaaS that anyone could use.   It’s called Daily Tracker and online at dailytracker.co. Just signup with an email address, password and supply your timezone and you’re in.   I’ve added some new reporting features to the tool to help you really dive into the data that you add.  New charts, reporting periods and artificial intelligence insights are now available. ~ New Reporting In addition to being able to look back over mood data for the current year with column charts, new reporting capabilities have been added. These feature different chart type such as heatmaps, tree maps, and word clouds are now available from the report menu:   Two clicks will let you access these. 30, 60, and 90 day reporting periods are available.   Selecting a reporting period will take you to detailed dashboard that contains insights from journal

  In this blog you will see how I converted a prototype application written in just a few hours to a production SaaS hosted in Microsoft Azure.   Before reading the rest of this blog, it will be useful to read these beforehand to get the full context:   Initial Idea (tweet) - Jamie Maguire on Twitter: Idea: A secure online journal that only lets you create one short entry per day. Single image upload optional. You can supply mood: sad, ok and happy. At the end of the year can look back over the last 365 days. / Twitter   Initial Prototype (blog) - How To: Creating a Private Journal and Mood Tracking App Using .NET 6, Chat GPT, C# and Visual Studio 2022 – Jamie Maguire   I’ve documented this for my own reference.  It contains the key steps and what it took to go from a web application running on my development machine to a SaaS running in the cloud.   This will be useful for you if you plan on shipping a similar product or want to know the steps you need to tak

In an earlier blog post, I introduced Audio Notes. This is a new a SaaS experiment that uses artificial intelligence, speech to text, and text analytics to automatically summarise audio and create notes from your recordings. In this blog post, I shared how you can use Azure AI Speech Services to perform continuous real-time speech-to-text transcribing. You will also learn about: speech to text transcribing options the JavaScript SDK main capabilities in the service key objects and events   A video demo is available along with full source code. ~ Azure Speech to Text Capabilities Real-time speech-to-text lets you transcribe speech from a microphone, file, memory stream. It can be used in scenarios such as: Creating, captions or subtitles in meetings Contact centres agent assistance Dictation ~ Single Capture Recognition Single-shot recognition lets you recognizes a single utterance. The end of a single utterance is determined by listening for silence at the end or until a maximum o

In an earlier blog post, I introduced Audio Notes.   This is a new a SaaS experiment that uses artificial intelligence, speech to text, and text analytics to automatically summarise audio and create concise notes from your recordings.   In the first part of this series, I showed how Azure AI Speech is used to perform real-time, continuous transcription of speech to text within the web browser.   In this blog post, you will see how transcribed text is summarized using Azure AI Language. ~ What is Azure AI Language? Azure AI Language is a service that encapsulates multiple Natural Language Processing (NLP) capabilities that help the machine understanding and analyse text. Previously, these were known as Azure Cognitive Service Text Analytics, QnA Maker, and LUIS. ~ What Is Document and Conversation Summarisation? I’m interested in in the document summarisation feature that is available.  An option to summarise conversations is also available.   Document summarization uses NLP

Skip months of foundational development and launch your SaaS idea in weeks, not months I've watched countless brilliant SaaS ideas die in the foundational development phase. Talented developers and i...

In an earlier blog post, I introduced Audio Notes.   This is a new a SaaS experiment that uses artificial intelligence, speech to text, and text analytics to automatically summarise audio and create concise notes from your recordings.   You can find more information about the project in these earlier blog posts.  These set the scene and show which Azure AI services make this end-to-end solution possible: Introduction Using Azure AI Speech to Perform Continual Speech to Text Transcription Using Azure AI Language to Perform Document Summarization   In this blog post (Part 4), you will see how I Blend Azure AI Speech Services and Azure AI Language Services to Create the Micro SaaS Audio Notes.  These are used to create a solution that automatically creates concise notes from the spoken word. Read on to see how all this hangs together. ~ Process and Overview To recap, the entire end to end process consists of the following steps: Clicking Start Recognition in

In the mid to late 90s, I ran a BBS on a Commodore Amiga 1200.  It started with 2 disk drives, and I eventually saved enough cash to get an IDE hard drive with a massive 520MB of storage. People from around the world would connect to that BBS on a single 36k modem.  About 80 registered users would dial into that BBS on a dedicated phoneline. I ran a Fidonet node that let user of the BBS send electronic messages globally.  This was before email and widespread internet access was available. Users would upload games, utilities, and public domain software.   There were no adverts. User data was not sold or analysed. There was no manufactured outrage. No algorithm to game. No Likes. Thumbs Up. Impressions or other vanity metrics. It ran on an isolated machine.     Screens were designed using ANSI graphics and menu navigation was simple. In this blog post, I document how to setup a BBS in 2024.  You will see how to use a budget Raspberry Pi, free software and services

What Is Semantic Kernel? Semantic Kernel had been on my radar for a while. Semantic Kernel is an open-source SDK designed to simplify the creation of agents that can interface with your existing code. The SDK is extensible and supports models from OpenAI, Azure OpenAI, Hugging Face, and more. Using the SDK means you don't have to learn the inner workings of LLM provider APIs. Semantic Kernel lets you build agents using C#, Python or Java.  Complex workflows and agentic AI orchestrations can be created using C#, Python or Java. With the open-source SDK from Microsoft recently reaching V1, now is the time to dig into what this can do. ~ Orchestration Layer Semantic Kernel sits at the centre of the agent stack.  It acts as the main orchestration layer for your agentic AI solution. AI models, and plugins (your existing code) can be easily integrated to help you create innovative solutions and user experiences. (image source Microsoft) In the past, this involved manually stitching together mul

This is different from my usual technical content but related. I had been considering getting a portable power station for a while now. I noticed that Jackery had a promotion running during Earth Day and decided to order the Jackery Explorer 1000 Portable Power Station. My main requirements were: upto a week power for a laptop multiple inputs and outputs option for solar panel connections   My order consisted of: Jackery Upgraded Carrying Case Bag for Explorer 1000/1000 Pro(M) Jackery SolarSaga 80W Solar Panel Jackery Explorer 1000 Portable Power Station   The total cost was £ 822.00.  In this short post, I review the Explorer 1000. ~ What Do You Get? The Jackery Explorer is designed for adventurers, outdoor enthusiasts, and emergency preparedness alike.  This power station offers a compact and robust source of electricity wherever you go. Ideal for my van adventures. The power station has 1002 watt-hour capacity and a versatile array of output ports, including: 12

If you are reading this blog, you probably listen to one or many podcasts. Some of my personal favourites include Seth Godin’s Akimbo, Lex Friedmans, Mike Tysons, and Andrew Hubermans. Most of these podcasts span multiple hours, and despite wanting to listen to or watch them, I just don’t have that amount of free time. ~ The Idea This got me thinking.  I could use AI to create a tool that would use speech-to-text to transcribe the audio.  I could then use AI to perform document summarisation on the transcription.   This would let me skim read the summarised points to get a feel for the main points, and outcome of the discussion points in the podcast.   I could use the summarisations to help me decide if the podcast was worth listening to. ~ CLI Tool In this blog post, you will see how I built a CLI tool using a combination of Azure AI services to save me hours each week.   Specifically, you learn about: Creating a CLI tool that accepts a podcast URL Batch transcription

I am partnering with Pluralsight again to bring you another new course soon. The course is called : Vector Databases & Embeddings for Developers. This course will come in at roughly 50 minutes.   ...

Build web apps and services that run on Windows, Linux, and macOS using C#, HTML, CSS, and JavaScript. Get started for free on Windows, Linux, or macOS.