I moved my AI orchestration gateway from a Tailscale funnel to Cloudflare Tunnel, locked it down with Access, and made Railway the only client that can reach it. The things that cost me time weren't in the docs. […]
Why you need different agents in separate sandboxes, why running them all from one chat window becomes a mess, and how a coordination layer (Paperclip) turned six isolated specialists into something resembling a team. […]
Three themes dominating every conversation with SRE and platform teams across ASEAN: defending against AI-generated exploits, reducing operational load with AI-assisted incident response, and understanding customer behaviour in mobile-first environments.
Everyone talks about AI prompts and smart models. Nobody talks about what actually makes agents work reliably: retry logic, error handling, failover chains, and the endless wiring that keeps everything from falling apart at 3 AM. Here's what I've learned running AI agents in production for months, and why most businesses shouldn't build this themselves.
I spent hours debugging why my AI agent couldn't use Google Workspace CLI in sandboxed mode. The breakthrough wasn't a clever workaround—it was building the right foundation. Here's what I learned about making sandboxed agents actually useful.
I tried building a professional setup without the enterprise price tag. It's not perfect, but it works and costs almost nothing. Here's what I learned along the way.
Most business owners don't own their website in any meaningful sense. The contractor does. The agency does. The CMS vendor does. But the infrastructure powering modern sites is now simple enough that an AI agent can manage it, and the shift changes who's actually in control. […]
Most people burn through Claude's limits re-explaining the same context every session. There is a built-in fix that Anthropic ships with Claude Code. Takes five minutes to set up and it carries everything forward automatically. […]
Using Claude feels expensive when the real problem is fragmented thinking. Most people burn through tokens doing five prompts to get something that one good prompt would have solved. I changed one habit and usage dropped significantly without losing quality. […]
I asked my agent to monitor baghunter.app with synthetic checks every five minutes. It worked, technically. Then I looked at what it was actually doing and realised I'd built something expensive and fragile. Here's what I changed. […]
Bag Hunter started as a question: could we ship a real product with a database, live UI, scraping logic, and price alerts without a traditional dev team? The answer is yes, with some asterisks that nobody in the AI content space wants to talk about. […]
AI-generated code is showing up as a contributing factor in incidents. The safety net needs to move closer to runtime. This month: AI Agent Monitoring, runtime security, and why the knee reflex matters for observability.
Most AI agents are cut off from the tools businesses actually run on. Google Workspace (Gmail, Calendar, Sheets, Drive) is where real work happens. Today I replaced gogcli with gws-cli, and for the first time, giving an agent full Workspace access feels like proper infrastructure. Here's what that unlocks.
I ran a large backfill on a Railway-hosted Postgres instance and the database crashed. Railway's volume resize UI said 5GB. The filesystem still said 500MB. Here's what actually happened and how I got 43,000+ rows back. […]
I burned through my Claude Pro subscription in three days. Then my Cursor Pro subscription the week after. Both $20/month, both gone before I'd even built half the features I wanted. The problem wasn't the subscriptions. It was that I treated every task the same. Used the premium models for everything, even when simpler models would work fine. Learning to match models to tasks changed how I build with AI.
I tried to have my AI agent do everything itself. Backend APIs, frontend UI, testing, code review, deployment. It could do all of it technically, but the results were slow and scattered. Context switching between tasks killed momentum. Then I realized I was thinking about it wrong. I didn't need one super-agent. I needed a coordinator and specialists.
Every time my AI agent started a new session, it woke up blank. No memory of yesterday's work. No context about ongoing projects. No awareness of decisions we'd made together. I'd spend the first ten minutes of every session catching it up. Explaining what we were building, what had already been tried, what didn't work. It was exhausting. The agent was capable, but it had no continuity. Every conversation was like meeting for the first time. […]
People ask me what I use my AI agent setup for. They expect exotic use cases. Autonomous companies running themselves. Agents negotiating contracts. Sci-fi stuff. The reality is more boring and more useful. I use AI agents for the repetitive work that eats up development time. Code reviews that catch the same mistakes. E2E testing that validates features. Coordinating work across frontend and backend. The stuff that's necessary but doesn't require creativity. […]
I thought giving my AI agent access to tools would be enough. It could read files, write code, run commands, search the web. Everything a developer needs. But after a few weeks, I noticed a pattern. It kept making the same mistakes. Asking the same clarifying questions. Forgetting lessons we'd already learned together. The agent wasn't getting better. It was just running in place. That's when I realized the problem. Tools without guidance are just capabilities without direction. […]
My AI agent was stagnating. It answered questions well but never got better at understanding me. So I built a feedback loop. Every afternoon, it asks what worked and what didn't. Over time, those small adjustments compound. Here's how I use scheduled prompts to make my agent improve every day. […]
Monthly update on observability trends, AI agent troubleshooting, and infrastructure monitoring insights
This year I'm committing to writing. Not as a New Year's resolution, but for life. Why? Because writing is one of the few ways I believe anyone can advance how they think. For me, it’s how ideas that would otherwise sit unexplored in the corners of my mind become something real. Writing forces those ideas […]
Monthly update on observability trends, AI agent development, and industry insights
Monthly update on observability trends, AI agent troubleshooting, and infrastructure monitoring insights
I have mixed feelings about the recent update. In case you missed it, Axie Infinity recently announced that it will bring back the V2 battler version, which started the biggest \"Play-to-earn\" wave. It returns with new mechanisms for earning tokens. Let's dive in. The updated Axie Classic has two main issues: Earning: You can only […]
Coming from the coal face of growth and business development — our humble team at XGlobal working with crypto startups — I've observed and tripped over more than my fair share of crypto-startup mistakes. Let's chat about them, one by one, in hopes you’ll avoid going down the same pot-holed paths where time is your scarcest resource.
Building competitiveness in your guild? Want to know how to rally the troops? Let's go through how people are motivated in a guild. Here's an excerpt of my own story and some practical tips and observations.
Thinking of starting an MMO guild? Do you know who will join you? Lots of transferable skills! Let's go through how people are the key ingredients of a guild. Here's my own story and some specific observations.
Thinking of starting an MMO guild? Do you also have experience as a corporate drone? Lots of transferable skills! Let's go through how you can take an idea and start your guild with a bang with my own story and some specific tips.
Comparing Two MMORPG Guild Archetypes: Socialist vs Capitalist
Playing an MMORPG competitively? Looking to dominate the open world boss but starting casual? Let's get you there with my own story and some specific tips to manage the hardest part of the game: people.