Adobe Firefly Just Became a Serious Automation Tool (And Most People Haven’t Noticed)
I’ve been skeptical of AI image generators. Not because they’re bad at making images—they’re terrifyingly good at that now. But because most of them sit in a weird gray zone where you’re never quite sure if you can actually use what you create. Then I started digging into what Adobe’s been building with Firefly, and […]
The Legacy Workflow: Why Connecting MCP Servers to Azure AI Foundry Used to Make Developers Cry
You know that feeling when you click around a new platform’s UI looking for a button that should obviously exist, and it just… doesn’t? Yeah, that was me staring at Azure AI Foundry’s interface, trying to connect an MCP server to my agent. There was no “Add Server” button. No form to input a URL. […]
I Built My First Production Claude Skill. It Writes This Blog.
When your AI assistant starts writing your blogs about building AI assistants, you know something meta is happening You know that feeling when you’re explaining the same thing for the tenth time and you think “there has to be a better way to do this”? That was me last week, staring at another client Slack […]
I Thought Claude Skills Were Just Fancy Prompts. They’re Actually Better.
There’s a special kind of professional exhaustion that comes from being really good at something: you end up answering the same questions over and over again. For me, that’s AWS architecture decisions. Every new client conversation follows the exact same pattern: Client: “Should we use Lambda or EC2 for this?”Me: Launches into my standard 5-minute […]
From $300/Month to Free: Rebuilding a Campaign Management System
Sometimes the best solutions come from the worst problems. In this case, that problem was watching a digital marketing agency’s SaaS costs spiral out of control because of one simple feature: client access. Here’s how I turned a $300/month Airtable portal into a completely free, secure campaign management system using Google Sheets, some creative automation, […]
Custom AI Chat Hub: Self-Hosting & Automation
This blog details the creation of a custom AI chat platform integrating Open WebUI with n8n workflow automation, securely exposed via Cloudflare Tunnel. It covers motivations for building a personalized conversational interface over existing options, the choice of core components (Open WebUI for chat UI, n8n for automation, Cloudflare Tunnel for secure access), and the architectural setup using Docker Compose with dedicated networks and persistent volumes. A key highlight is the seamless integration enabling function calls from chat to trigger n8n workflows via webhooks without extra middleware. The blog also discusses DNS and proxy configuration challenges, container-specific nuances, security best practices, and lessons learned during setup. The resulting system offers a flexible, maintainable, and secure AI command center with persistent sessions and natural language automation interaction, primed for future enhancements including local model hosting and expanded API integrations.