Arin's Tech Musings

GitHub Copilot's customization system separates into four distinct layers: custom agents, instructions, skills, and MCP servers. Each handles a different concern, and they compose together while remaining independently upgradeable. The key insight: separating "who" (agent workflow), "rules" (project standards), and "how" (capabilities) means you can change one without touching the others. Update standards without rewriting agents. Upgrade skills without modifying instructions. Change agent behavior while keeping conventions intact. Everything lives in git. Changes go through pull requests. You can review, approve, and roll back AI behavior like infrastructure. > **Honest disclaimer:** The thoughts here are mine — the prose, structure, and general readability are courtesy of AI. I handed it a brain-dump and it handed back something you'd actually want to read. ```mermaid graph TB subgraph "GitHub Copilot Architecture" ...

GitHub Copilot custom agents make it possible to move beyond a single “do everything” assistant. Instead, you can design workflows where multiple agents collaborate, each focused on a specific responsibility. In this post, I’ll walk through three orchestration modes you can use today when building custom agents in VS Code: VS Code agent handoffs Explicit subagent delegation Automatic subagent delegation Each mode serves a different purpose. Understanding the trade‑offs helps you decide when you want user control, when you want structure, and when you want the agent to adapt on its own. 1. VS Code Agent Handoffs ```mermaid sequenceDiagram participant User participant MainAgent participant SecurityAgent User->>MainAgent: scan my code for security issues MainAgent->>SecurityAgent: handoff (code review) SecurityAgent-->>MainAgent: report findi...

  According to the World Economic Forum, we are going through the Fourth Industrial Revolution (4IR). 4IR will feature major technological advances in artificial intelligence, robotics, genomics, materials sciences, 3D printing, and more resulting in businesses, governments and civic institutions to collect, store and analyze data at an unprecedented scale, speed and depth. Public cloud computing is the engine that powers and enables the realization of these technological advancements and its adoption. With new rules/directives like the EU Corporate Sustainability Reporting Directive (CSRD) requiring all large companies to disclose their impact on people and the planet, it is only imperative that we don’t stop at only using cloud solutions to track emissions but also look at how to measure and reduce carbon emissions from our software and data footprint in the cloud.  "It’s time to start seeing software as part of the climate solution and not as part of the climate problem." ...

 If you have used or are still using Azure AD PowerShell for interacting with Azure AD, you should probably already have taken note that Azure AD PowerShell will be deprecated on June 30, 2023. The alternative - Microsoft Graph PowerShell SDK, uses the power of the new Microsoft Graph and all underlying Graph APIs - allowing you to do much more than just Azure AD related tasks, supports PowerShell 7 making it work cross platform, use modern authentication and a whole bunch of other things that you expect from a modern solution. See link to learn more: https://learn.microsoft.com/en-us/powershell/microsoftgraph/overview?view=graph-powershell-1.0 The SDK supports two types of authentication: delegated access and app-only access. If you follow the tutorial in the documentation, you will be using the delegated permission model. This is effective for ensuring least privilege. However, there is one important thing when dealing with delegated permis...

 Azure API Management offers caching possibilities to improve performance.  There are 2 caching options: Response Caching - Useful for caching entire HTTP responses Value Caching - To cache arbitrary pieces of data from within policy definitions. When it comes to the actual store, APIM supports: Built-in cache External Redis Compatible cache In this blog I will focus on how to manage "Value Caching". How do we set/retrieve/delete values using APIM policies? Typically, Value storage is used for fragment caching - where responses contain data that is expensive to determine and yet remains fresh for a reasonable amount of time. Also, within the APIM policies, we want to cache certain values e.g. OAuth tokens, key-vault secrets, etc. because these remain relatively fresh for a longer period of time. With caching comes the need to manage the cache specially when you need to clear cached values because they are stale.  In some scenarios, where OAuth tokens or secrets are cached...

 When hosting APIs in Azure it is more and more common to make them available for consumption via an API Management Gateway. The advantages of using a API Management gateway are well known.  When adding a Function/WebAPI to an API Management gateway, the most common method is to add the Function/WebAPI as a backend in API Management and then exposing the Function/WebAPI as an API that uses this backend to process requests. There is a very simple way to do this using the Azure Portal. The portal allows connecting an existing Function or WebAPI inside the API Management gateway.  The portal now also allows to expose a function/web api from the action pane of functions and web api. While this makes it very easy to add APIs to API Management gateway using the portal, this would very soon become unmanageable and for more complex and automated environments, the obvious tilt would then be towards a automated deployment using one of the Infrastructure as Code (IaC) possibilities....

 For those of use that use or have implemented an Azure API Management instance, one feature that we have all looked for is a way to perform "Request Schema Validation" for incoming requests. Quite strangely, this much wanted feature is not a part of Azure API Management yet, although, there has been a User Voice request open since 2016 but the item is still marked as "Under Review". If you want to vote for this feature, you can Vote Here . Although this feature has not been picked up by Microsoft engineers yet, this has not in any way dampened the enthusiasm around Azure API Management as an API Management tool. And as with most things, the community adapted and found workarounds to achieve what they otherwise expected out of the box. In this blog, I will first describe the most common workaround and also the limitations that you might run into with it. Then of course, I will share how I circumvented this limitation with another workaround. Using a Logic App The mo...