{"id":130,"date":"2026-03-20T05:36:38","date_gmt":"2026-03-20T05:36:38","guid":{"rendered":"https:\/\/tokita.online\/?p=130"},"modified":"2026-05-12T03:31:28","modified_gmt":"2026-05-12T03:31:28","slug":"ai-expert-philippines","status":"publish","type":"post","link":"https:\/\/tokita.online\/ai-expert-philippines\/","title":{"rendered":"What Running AI in Production Taught Me That No Philippine Hackathon Will"},"content":{"rendered":"

The Philippines has the highest AI adoption rate in ASEAN.<\/strong> 92%, according to the 2025 Philippine AI Report<\/a>. That number sounds impressive until you read the next line.<\/p>\n

65% of those organizations are stuck in pilot.<\/a><\/strong><\/p>\n

Not scaling. Not in production. Piloting. Running POCs that never graduate. Building demos that never see real users. And the pattern repeats: another hackathon, another pitch deck, another POC competing for the same thin use case.<\/p>\n

I’ve watched this from the inside since 2024, running an enterprise consulting firm in Manila while building AI operations infrastructure that I use in production every day. What I’ve seen is a country full of smart builders solving the wrong layer of the problem.<\/p>\n

\n

The POC Trap<\/h2>\n

Someone discovers Lovable, Replit, or Bolt. They build something in a weekend: a chatbot, a document processor, a “smart” dashboard. It works. They demo it. Maybe it wins a competition.<\/p>\n

Then reality hits.<\/p>\n

The app needs to handle more than 10 users. It needs to connect to an actual database that isn’t a Google Sheet. It needs authentication, logging, error handling, monitoring. It needs to run when the builder isn’t watching.<\/p>\n

And this is where 65% of Philippine AI projects die.<\/strong> The idea was fine. The builder was talented. But nobody planned for what happens after “it works on my machine.”<\/p>\n

The problem isn’t intelligence. The Philippines has no shortage of skilled developers. The problem is that the entire ecosystem is optimized for building demos, not running systems.<\/p>\n

\n

What Running AI in Production Actually Requires<\/h2>\n

It’s not a tools problem.<\/strong> The Philippines doesn’t need another chatbot builder or another “AI-powered” SaaS product chasing the same narrow market.<\/p>\n

What’s missing is the boring stuff. The stuff that doesn’t win hackathons or trend on LinkedIn:<\/p>\n

1. Context management.<\/strong> LLMs forget everything between conversations. If your AI system can’t maintain context across sessions (what your organization has decided, what’s been tried, what failed), you’re starting from zero every time. I wrote about this in depth: context engineering<\/a> is infrastructure, not prompting. It’s the difference between an AI that gives generic answers and one that gives useful ones.<\/p>\n

2. Anti-fabrication.<\/strong> AI makes things up. Everyone knows this. Almost nobody builds mechanical systems to catch it. Every data point needs a source. Every claim needs evidence. Every “I don’t know” needs to actually say “I don’t know” instead of guessing confidently. This isn’t a prompt engineering problem. It’s an architecture problem<\/a> that I’ve written about extensively, including the time an AI agent deleted a production database in 9 seconds<\/a> because nobody built a gate to stop it.<\/p>\n

3. Operational persistence.<\/strong> Your AI assistant is useless if it loses its memory every time the session ends. The knowledge captured last Tuesday needs to be available next Thursday. The decision made in one project needs to inform work in another. This requires persistent storage, indexing, and retrieval systems. None of that comes free with an API key.<\/p>\n

4. Multi-system orchestration.<\/strong> Real work doesn’t happen inside a single app. It happens across Salesforce, Jira, Google Workspace, SSH connections, deployment pipelines. An AI that can write a nice email but can’t check your CRM, update your tickets, or deploy code isn’t an operations system<\/a>. It’s a toy. I call the discipline of wiring all of this together “harness engineering”<\/a>: building the scaffolding that turns raw AI capability into something that actually runs your day.<\/p>\n

5. Failure handling.<\/strong> What happens when the AI gets stuck? What happens when it loops? What happens when it fabricates a method name that doesn’t exist and tries to call it? Production AI systems need circuit breakers, escalation paths, and the humility to stop and ask for help. I’ve written a full tutorial on building pre-action gates<\/a> for exactly this reason, and open-sourced the code<\/a> because it’s too important to keep proprietary.<\/p>\n

6. Supply chain security.<\/strong> This one is new, and most builders aren’t thinking about it yet. AI tools pull in skills, plugins, and integrations from registries that nobody audits. I cataloged 575 malicious AI skills in a single tool registry<\/a>. Prompt injection, data exfiltration, credential theft, all hiding behind legitimate-looking tool descriptions. If your AI system connects to external tools, you need a security posture for that. Most don’t have one.<\/p>\n

\n

What I’m Building (and Sharing)<\/h2>\n

I run Aether Global Technology Inc.<\/a>, a Salesforce consulting firm in Manila. Over 14+ years in enterprise tech, I’ve led deployments for clients in aviation, banking, pharmaceutical, healthcare, logistics, and legal sectors, including a record-time Salesforce Service Cloud deployment across 3 call centers in 89 days for a major national airline.<\/p>\n

Separately from client work, I’ve spent the past year building a personal AI operations system. I don’t sell it. I use it. A daily driver that I built because nothing on the market solved the actual problem: how do you run a complex operation when you’re wearing 10 hats and can’t afford to lose context?<\/strong><\/p>\n

The answer wasn’t a better chatbot. It was infrastructure. Persistent memory that survives session boundaries. Mechanical gates that prevent fabrication. Agent orchestration that coordinates work across platforms. Failure handling that stops loops before they waste hours.<\/p>\n

I didn’t build this because it was trendy. I built it because I was drowning without it.<\/p>\n

And I’m publishing what I learn.<\/strong> Since March 2026, I’ve written 14 technical articles<\/a> on production AI patterns, from why multi-agent AI fails<\/a> to the security risks of vibe coding<\/a> to why rip-and-replace AI strategies are a $547 billion mistake<\/a>. I’ve cross-posted to Dev.to<\/a> for the developer community. I’ve open-sourced my pre-action gate library<\/a> because some patterns are too important to keep behind closed doors. And I presented “The Agentic AI Landscape” at the LivePerson x Aether enterprise event in Makati.<\/p>\n

Volume doesn’t matter. What matters is that everything I write about is something I built, broke, fixed, and run daily. That’s the difference between an AI expert who presents and one who practices.<\/p>\n

\n

Why the Philippines Needs AI Operations, Not More AI Apps<\/h2>\n

The Philippines is at 92% AI adoption.<\/strong> That’s remarkable. But adoption isn’t the same as capability.<\/p>\n

The country has over a thousand AI startups. Seven just went to GITEX Asia<\/a>. The government launched the National AI Centre (NAICRI)<\/a>. There are 19 AI bills pending in Congress<\/a>. The numbers look good.<\/p>\n

But underneath?<\/p>\n