AI Development on Nick Perkins

I Stopped Using MCPs and Replaced Them with Skills and Scripts

Sat, 20 Jun 2026 10:00:00 +1000

Everyone’s excited about MCPs. The Model Context Protocol is supposed to be the standard way AI agents talk to external services. And it is good, for what it is. But I’ve been replacing MCPs with skills and scripts in my own workflows, and honestly, I’m not going back.

The problem with MCPs

When you load an MCP server, all of its tool definitions get injected into the agent’s context. Every tool name, every parameter schema, every description. The Atlassian MCP alone exposes dozens of tools across Jira and Confluence. That’s a lot of schema sitting in your context window before you’ve even asked the agent to do anything.

grug make AI skill. grug happy.

Mon, 06 Apr 2026 10:00:00 +1000

grug been thinking about complexity demon lately. complexity demon sneaky. complexity demon hide in code review. complexity demon whisper “just add one more abstraction.” grug not listen.

grug make thing. thing called grug-brain.

what thing is

grug-brain is AI skill. you give skill to AI, AI become grug. AI then fight complexity demon with you.

AI will:

look at code, say if too complex
suggest simpler way
explain things in grug speak
not add factory pattern when simple function fine

grug inspired by grugbrain.dev. you should go read. very wise. grug just made it easier to load into AI assistant.

The Testing Pyramid Still Matters (Even When AI Wrote Your Tests)

Sat, 07 Mar 2026 10:00:00 +1000

I’ve been spending a lot of time in agentic AI workflows lately. Describe a feature, the agent writes the code, the tests, and the PR. It’s genuinely impressive. And the test suites are taking fifteen minutes to run, full of integration tests that didn’t need to be integration tests.

The testing pyramid didn’t become irrelevant just because AI wrote the tests.

The problem with AI and test placement

AI agents are enthusiastic testers. Ask one to add coverage for a new feature and it’ll write tests, lots of them. The problem isn’t that they default to any particular layer. It’s that they’re trained to optimise for quality and coverage, not for the cost of achieving it. Nobody’s system prompt says “think about how long this test suite will take to run.” So they go overboard. Spinning up a database, creating records via factories, hitting an HTTP endpoint, asserting on the response. It works. The test passes. But it’s expensive.

AI and the Human Factor - My Observations

Wed, 20 Aug 2025 10:00:00 +1000

Over the last year, I’ve been watching how people use AI coding tools. GitHub Copilot, ChatGPT, Claude - everyone’s got access to them now. But the results? Completely different depending on who’s using them.

Here’s what I’ve noticed: the engineers who were already good are using AI to get even better. The ones who struggled before? They’re producing questionable code at an incredible rate now.

AI just amplifies what you already are

AI tools can be amazing productivity boosters. I’ve seen junior developers build features in hours that used to take days. Senior people are prototyping stuff at lightning speed.

Building Interactive MCP Tools with Elicitations: A Practical Guide

Fri, 11 Jul 2025 22:00:00 +1000

The Model Context Protocol (MCP) is revolutionising how we build AI tools, but a powerful new features recently added to the protocol will be a game changer: elicitations. These enable your MCP tools to have interactive conversations with users, gathering input dynamically rather than requiring all parameters upfront. Let me show you how to build engaging, interactive MCP tools using a practical ice cream topping recommender as our example.

What Are MCP Elicitations?

Elicitations in MCP allow tools to prompt users for additional information when needed. Instead of failing when required parameters are missing, your tool can ask the user to provide them through a structured interface. This creates a more natural, conversational experience with AI assistants.

How I Built Interactive AI-Powered Training with GitHub Copilot

Fri, 27 Jun 2025 00:00:00 +0000

One of my current projects is a migration from Azure DevOps to GitHub Actions. I saw a challenge: how to effectively train DevOps teams on new tools in an engaging, practical way? Traditional docs and tutorials often miss the mark. So, I experimented: using GitHub Copilot’s Agent Mode to build an interactive, AI-powered training platform. The result was a self-paced, conversational learning experience, guiding users through complex migration scenarios like having an AI tutor.