AI Agent Night, Hermes Edition: 650 People, Seven Speakers, and the Questions That Matter Now

Before AI Agent Night even began, I was probably the most excited person in the room. 🙌 It's rare to see a line-up this good packed into one evening. 650 people from 1,300 signups filled the space for our third AI Agent Night, Hermes Edition, put together by Lionel Sim and The AI Capitol community at AWS. AI agents are no longer on slides - they're in production, running real work, making real decisions, and moving real money.

Seven speakers, completely different backgrounds, all shipping real things. I wrote this full reflection to democratize the learnings for everyone who came and wants to go deeper, everyone who couldn't make it, and everyone who's been watching the posts fly by.

The Speakers and What They Shipped

Each talk surfaced a different angle on the same reality: agents are here, and the work now is making them safe, scalable, and sustainable.

🔹 Bryan Chua (GoPomelo) - running a multi-tenant fleet of agents in production, with token caps and security locked down from day one.

🔹 Nathaniel Ng - spec-driven development with Kiro: get your requirements right and the code follows.

🔹 Benjamin Cheng (Sandpiper) - a finance director, not an engineer, automating debtor tracking and compliance questionnaires… on a 10-year-old laptop with a broken screen.

🔹 Marcus Cheu (Notion) - turning a personal agent into team capability by giving everyone one shared 'second brain.'

🔹 Amarnath R. (Airwallex) - agents that touch real money safely, with server-side human approval before anything moves.

🔹 Jasper Hartono - sent a WhatsApp from a pair of AR glasses just by looking and speaking. The room's favourite by a mile. 🕶️

The Questions That Surfaced in Every Talk

Here's what struck me: nobody was asking 'can agents do this?'

They were asking how do I run this responsibly - without my token bill exploding, without losing the thread on long tasks, and without handing over keys I can't take back.

⚖️ Cost. Memory. Trust. The same three worries surfaced in every single talk.

That's a technology growing up.

What This Means for All of Us

The builders in that room weren't chasing hype. They were solving real constraints - budget, compliance, handoff clarity - with agents that amplify human judgment instead of replacing it.

Benjamin's story hit hardest for me: a finance director with a broken laptop, no engineering background, and a clear problem to solve. He built an agent that works. That's the future I want to see - AI that meets people where they are, not where the vendors wish they were.

💡 If you're building with agents right now, you're not alone. The questions you're wrestling with - cost, memory, trust - are the same ones every production team is facing. And that's exactly why nights like this matter.

More Soon

I've written a full reflection article with every session, the framework I opened with, and the honest behind-the-scenes bits. If you were there, I hope it helps you go deeper. If you couldn't make it, I hope it brings you into the room.

What are you building with agents right now? I'd love to hear what's landing for you - and what's still hard. 🙏

#AlwaysDay1 #AIAgents #AgenticAI #ProductionAI #AILeadership #FutureOfWork