Tony Tang
Writing

Writing

Code is cheap, show me your idea.

Published October 2026 · 1 min read

Writing code was a craft. That craft was the joy of being an engineer.

AI is taking the joy of writing code away, and soon enough it will take the joy of reading code too. Engineers are turning into managers: we talk to different agents (harness sessions) to make a wish, armed with the skills and taste we built up from years of enjoying that craft.

When I first became a solution architect, it did feel like an upgrade to a role that creates more essential value: design and architecture. Ironing out the tech design and leading the team to build it in 6 sprints brought real joy. AI hasnt taken that away (yet). But soon enough, some agents will be upgraded to planning agents (the architect), and cheaper models will carry out the actual building.

Craft → Copilot → Vibe → YOLO → Idea engineering.

Limited joy means limited growth as a technical person. Our taste came from years of the craft: writing code, reading code, shipping it and putting out the fires. For future engineers, if the craft is gone, where does taste come from?

We used to say: talk is cheap, show me the code.
Now: code is cheap, show me your idea.

Zen and the Art of Agent Engineering

Published June 2026 · 2 min read

Early this month, I was in the Himalayas for 冈仁波齐转山: the kora around Mount Kailash.

Sacred to four religions. Walked clockwise by pilgrims for over a thousand years. Not supposed to summit.

Day one at altitude. Gasping for breath, thinking about agents. What we face had older names already.

缘起: Dependent Origination

Nothing arises in isolation. There is no "the agent": only this model in the harness, with prompt, tools, memory. Change any condition, behavior changes.

Context engineering, harness design: these are just dressed-up words for arranging the conditions deliberately.

无明: Fundamental Ignorance

Most engineers treat hallucination as a bug. It isn't. It is the model's ground state: a system trained to predict what sounds right has no way to tell "I know this" from "this sounds like something I'd know."

More parameters won't fix this. It is the system seeing its own limits: calibrated uncertainty, grounded retrieval, honest refusal.

无常: Impermanence

What worked yesterday might not work tomorrow.

The Sword of Damocles hangs over every engineer in 2026. We are worried about being outpaced. And yet we choose to learn, build, and ship with LLMs every day. 成住坏空 (arising, abiding, changing, ceasing) has come for our profession. We just happen to be living through the arising.

戒定慧: The Three Trainings

  • 戒 Discipline: What the agent cannot do. Auth gateway, policy engine, kill switch.
  • 定 Concentration: Single purpose, narrow scope. Whatever tries to do everything does nothing well.
  • 慧 Wisdom: Knowing when the sandbox itself needs to change, not just the contents. The hardest layer to automate. Without it, you build the wrong thing well.

· · ·

Summiting 冈仁波齐 was never the right verb.

The trail is slope after slope. The hardest part isn't the slope you're climbing. It's the next slope, already visible up ahead, while you're still gasping through this one.

Agent engineering is a kora. Every slope teaches what the last one couldn't.

The practice is the work.

#AgenticAI #Zen #MountKailash

‹ Back to work
Made with