AI for developers and Architects

The cost of prototypes is unbelievably low using AI. 

Rapidly creating a prototype, especially with new or less well-known technology, is where I derive significant benefits from AI.

How to build application prototypes?

1. Write /reverse prompt/Adjust instructions into md file
2. Agentic AI (specialising in Doc Extraction) to extract and refine from md file
3. Run using IDE-based copilot (VS Code with GitHub Copilot) (AmazonQ) (Cursor, Windsurf, Steamlit) 

Thoughts: Developers are adjusting to using Ai to support software solutions.  The developer role will continue the trend of making technical implementation more accessible, allowing knowledgeable IT engineers or domain experts to build faster and better than citizen/amateur developers.  Ai assists in complex decisions!  

What needs to improve?

• Knowledge is key.  AI needs to have narrow expertise at the right time. i.e. only domain knowledge, not influenced by other data.  Quality of input data used to train.  Allows for dynamic reasoning.
• Session/long-term contact agreement/understanding to improve the understanding between your IDE and me.  Remember how I prompt and provide feedback on how I digest information.  Context between the human developer and Ai is Paramount.
• Control of IDE integration with coding copilots, clear return to the user developer to make better decisions.  Context is Paramount.
• Governance & Data (Connectors, API's, code complex processes (MCP maybe), quality of data).

Retrieval Augmentation Generate (RAG)

Pulumi to create App Insights on Azure with VS Code

Overview: Provision Azure App Insights using Pulumi on VS Code using TypeScript, code generate by Pulumi's AI web code engine.  It is so lovely. 

Series on Pulumi:

Introduction and setup Pulumi on VS Code

Pulumi to create App Insights on Azure with VS Code (This post)

OpenAPI Tooling working with WebAPI and APIM Notes

Editor.swagger.io is a great tool for building OAS files.  The Swagger editor is easy to use and has a preview for changes.

VS Code is a great IDE for working with OpenAPI  specification 2.0 and 3.0 files (also know and Swagger specification).  These 3 extensions are a good idea for working with a OpenAPI specification file.

Spotlight also has an editor which is nice.  Takes a little bit of getting use to, but make complex API design first easier.

Azure Powershell from VS Code

Overview:  I am moving over to using Visual Studio code for everything including PowerShell.  Historically, I would use PowerGUI as it was the best IDE for PS for many years but PS ISE is excellent and I don't see a material difference these days.  Basically, I use VS code for my ISE for JS, SPFx, C# unless the full versions of Visual Studio speed up my delivery rate, this allows me to remain in VS code without going to PowerGUI or 1 of the Windows PS consoles/IDE.

Get the VS code debugger working: 

Get the IDE (VS Code) ready
On a new VS Code install, add the VS Extension "PowerShell", the VSIX has the description "Develop PowerShell scripts in Visual Studio Code!"

Run and Verify PS is working and output returned is working

Add the Azure Account Extension

Sign into Azure

A notification pops up to authenticate the machine/laptop with you Miscrofot credentials.  Run the popup and sign in to authenticate the local dev IDE.

 Open the Cloud Shell

Verify you are signed in

Visual Studio Code - IDE Tips

VS Code - Short cuts

Ctrl + S = Save the current page

Alt+ Shift + A = Comment out multiple lines

Ctrl + / = Comment out a single line of code, same cmd to toggle the comment off

VS Code is perfect for comparing two files.  Select the two source file, right click > Select to Compare >