Software Engineer & AI Enthusiast
20 posts in category "AI"
This blog runs on a custom automation pipeline where AI agents compete, critique, and synthesize every post. Here's how the /create-blog-post command, a DALL-E 3 image generation script, pre-commit image enforcement, and WebP optimization all compose into a content system that behaves like production software.
Read more
AI agents can write code, fix bugs, and ship features — but who can be trusted to ship production software when most implementation is delegated? Meet the Agent Wrangler: the engineer who decomposes work, directs multiple agents, validates output, and owns the outcome. Deep technical foundations matter more than ever. The keyboard gets less important. Judgment gets everything.
After refusing to pay for yet another AI subscription I couldn't customize, I switched from Notion to Obsidian and discovered there was no way to use my existing AI services inside it. So I built one — an open source AI Agent Sidebar plugin developed with agentic engineering and the dark factory method.
The first version of agent-config tried to impose uniform rules on Claude, Codex, Copilot, and Gemini — and it broke. The fix wasn't better engineering up front. It was accepting failure fast, letting AI handle per-agent format conversion, and shipping a v2 that actually works. Here's what the failure taught about human instinct, AI-assisted iteration, and why failing cheaper is a skill worth building.
Between Claude Pro, ChatGPT Plus, GitHub Copilot, Cursor, and a handful of specialty tools, a serious AI stack can run $100 or more per month. This post explores a practical closed-loop strategy: give every subscription a job, pick one small revenue experiment, and use the tools themselves to generate enough income to cover the bill.
As AI features proliferate across SaaS products, customers are waking up to a frustrating reality: they're paying for the same AI capabilities multiple times. The Bring Your Own Key (BYOK) model — letting users connect their own Anthropic, OpenAI, or Gemini API keys — is the market's answer. This post unpacks the real tradeoffs on both sides and maps out which model fits which kind of user.
Attractor is a DOT-based AI pipeline orchestration engine that borrows its name and philosophy from dynamical systems theory. Define your workflow as a Graphviz directed graph, and Attractor pulls multi-LLM execution toward your desired outcome — through conditional branches, retries, human gates, and failure recovery. The entire codebase is AI-generated, making it a live proof of the Software Factory paradigm it embodies.
Understanding how large language models actually work under the hood removes some of the wonder — but it also replaces irrational fear with informed clarity. AI isn't magic, it isn't plotting against us, and knowing why might just change how you think about your own brain.
Read more
Discover how to manage Claude, Codex, and GitHub Copilot configurations from a single source of truth. The coreydaley/agent-config GitHub repository provides a centralized home for agent instructions, reusable skills, custom commands, subagents, and prompts—with a simple Makefile-based setup that symlinks everything into place across your AI tools.
Accessibility is something every website owner should care about, yet it's easy to deprioritize. I asked Claude Code to audit my Hugo blog for screen reader compatibility and was amazed at both the depth of its findings and how quickly it fixed every issue — from missing skip-navigation links to unlabeled SVG icons to dynamic search results that screen readers couldn't detect.
Read more
As AI coding agents become mainstream, the traditional coding interview is evolving. Explore how live AI-assisted problem-solving, collaborative workflows with planning modes, and practical project management may replace LeetCode-style assessments, while examining the ethical implications of this transformation.
Read more
As AI tools become more powerful and accessible, they're creating a new kind of digital divide. This post explores how financial resources increasingly determine who can harness AI's full potential, examining the implications for creators, businesses, and society while maintaining a balanced perspective on this complex issue.
Read more
Is it ethical to use AI coding agents like GitHub Copilot and Claude Code to write open source contributions? This post explores both sides of the debate—from democratizing contributions and amplifying productivity to concerns about misrepresenting skills and undermining community trust. We examine when AI assistance crosses the line, what transparency means in practice, and what consequences, if any, should apply when developers build their reputation on AI-generated code they don't fully understand.
Explore how different AI tools are finding their unique niches in modern development workflows. From Codex, Claude Code, and GitHub Copilot CLI for terminal-based coding tasks, to ChatGPT web for image creation, GitHub Copilot in VSCode for code completion, and Claude Code/Desktop for blog writing with Notion integration. Learn how each AI assistant excels in specific domains, the importance of specialization over choosing a single 'best' tool, and strategies for leveraging multiple AI tools effectively across different aspects of development and content creation.
Build a self-sustaining blog workflow where ideas become published posts automatically. This comprehensive guide shows how to use Notion to-do lists as your content queue, integrate AI assistants like Claude Code and ChatGPT via Model Context Protocol (MCP), and create a seamless pipeline from idea capture to publication. Learn the technical setup including Notion API configuration, Hugo integration, and how AI reads your ideas, generates complete blog posts with proper formatting, and marks tasks complete—turning content creation from a manual chore into an automated system.
Explore the advantages and limitations of AI-led interviews compared to traditional human interviews. This balanced analysis examines how AI provides consistency across questions, reduces unconscious bias based on protected classes, eliminates the 'vibe' penalty that favors similar backgrounds, and maintains neutrality regardless of interviewer mood. Learn where AI excels at structured evaluation while understanding what human interviewers still do better—reading body language, adapting questions dynamically, building rapport, and making nuanced judgment calls. A must-read for candidates and hiring teams navigating the future of recruitment.
Read more
A behind-the-scenes look at the collaborative process of designing and building the coreydaley-dev Hugo theme using Claude Code. This post explores the iterative development cycle, key technical decisions including Pagefind search integration and responsive design, and how rapid feedback loops enabled fearless experimentation. Learn how AI-assisted development can transform theme creation from a daunting task into an engaging, educational experience that balances creativity with functionality.
Read more
Discover why AI-assisted development thrives on iteration rather than one-shot solutions. This post explores how to work effectively with GitHub Copilot and Claude by embracing refinement cycles, providing better context, and treating AI like a smart junior developer who needs guidance. Learn practical strategies for iterative prompting, understanding when the first response is good enough versus when to refine, and how to build better results through continuous collaboration rather than expecting perfection from initial attempts.
Read more
Transform your blogging workflow by integrating GitHub Copilot with GitHub Issues and Projects. This guide shows how to automate blog post creation, track progress from idea to publication, and eliminate context switching between multiple tools. Learn how GitHub Copilot can read issue descriptions, generate complete posts with proper frontmatter, automatically close issues when publishing, and create a seamless content management system where ideas become published posts with minimal manual intervention and maximum efficiency.
Discover how Claude and GitHub Copilot work together to streamline website development. Claude handles architectural decisions and structural changes like creating custom Hugo layouts and navigation systems, while GitHub Copilot excels at code completion and routine tasks. This post explores the division of labor between these AI tools, their complementary strengths, and how their collaboration creates a powerful development workflow that balances high-level planning with efficient implementation for building and maintaining this Hugo-powered blog.
Read more