AI Native 组织观察站

"Even when you use a coding agent to write all your code, understanding software fundamentals is important for steering your agent to make the tradeoffs you want — or to even know what tradeoffs exist to be made."

"Back in Nov 2025 I fully stopped writing code by hand, though I continue to code (using agents) every day. That is the point where for me and many others around me, it felt fair to say that coding is solved. But engineering is more than coding."

"In 2025, I thought I'd hate having AI write my code, because I thought it meant autocomplete in an editor. I still hate that style! Now it means agents doing the work, and I love it."

"Agents can skip much of that work, so building your reps has to be deliberate. Good agent work depends on two abilities: 1. Deep expertise… 2. Applied judgment… To build these the skills I'd practice are decision making, specifying, steering and verifying."

"In the next chapter of software engineering, agents will become proactive by default, software will improve itself, and compute will automatically get allocated toward the highest impact use cases. We're still at the dawn of the self-driving software era."

"You can now run Cursor cloud agents on your infrastructure, including pools of machines that automatically scale with demand. This lets you give agents access to internal services or specialized hardware, while the agent loop stays in Cursor."

"I love agentic coding harnesses, but they shouldn't be primarily terminal-based. The terminal is great for quick and precise commands, but information density is extremely low and UI affordances are minimal."

"Sorry for the radio silence folks - got sucked into extreme LLM psychosis. But I can confidently say we have crossed over into a new age of AI Engineering and we are never, ever, looking back."

"Looking for an AI-native SDLC playbook? @AnthropicAI just published a detailed one. It keeps the standard SDLC stages (plan/design/build/test/deploy/maintain) but reframes the process from a linear flow to artifact-driven loop."

"Yeah, increasingly a lot more appealing to tear down these abstractions now that agents can do a lot of the math and drudgery and verification. A lot of the abstractions were built for a world with constraints of finite intelligence and attention in the industry."