Posts

Developer experience became a competitive moat in the API era. Agent experience is next. Most tools aren't designed for it yet.

Ask for bugs and you'll get bugs — whether they exist or not. Sycophancy is a design feature, and the fix isn't better prompting.

The most dangerous person in an AI consulting engagement knows how the model works but has never sat in a credit committee.

Hong Kong has quietly run one of the most sophisticated GenAI experiments in global banking. Almost no one outside the region is paying attention.

Most enterprise AI agent pilots in financial services fail at the same point: the second tool call. The problem isn't the framework.

Banks are deploying RAG for compliance and discovering the hard problem isn't retrieval. It's the pipeline before it.

The operational instincts built in production banking don't belong in the past. They're exactly what makes a practitioner-turned-consultant useful.

The real project isn't artificial intelligence. It's the data infrastructure that AI exposes as broken.

We're building parallel interfaces for the same functionality because humans and AI agents parse the world through fundamentally different grammars. The future isn't human OR machine interfaces - it's both, simultaneously.

The real revolution isn't making AI smarter - it's making it invisible

LLMs aren't just tools we prompt - they're forcing functions for human linguistic evolution

The protocol that looks like plumbing but acts like philosophy - how MCP fundamentally changes the agent-tool relationship

When AI can execute complex setups through conversation, learning shifts from reading documentation to observing execution.

When AI coding assistants become workflow orchestrators, the most powerful compiler processes reality, not code.

Walking meetings, voice input, and location changes unlock cognitive advantages desktop workflows can't access.

AI becomes most powerful when it helps you discover what your ideas actually are. Cognitive partnership over replacement.

Why I use Claude Code for everything except coding: cognitive compiler for strategy, decisions, and understanding.

Building AI systems that work in the real world requires thinking beyond the demo. What actually matters when users depend on your models.

When artificial intelligence becomes as mundane as running water, how does thinking itself change?

When implementation becomes automated, human intelligence reallocates to purpose and strategy. The cognitive hierarchy inverts.

When algorithms shape decisions we think are ours

The automation tool that creates more coordination work

The authentication systems we're building assume AI agents are tools. What happens when they become economic actors with their own accounts, credentials, and legal standing?