Hi, I'm Limin Ge. Founder & Engineer building products people use, play, and pay for.

Founder notes

AI-Native Engineering: 11 Hard Truths for 2025

Principles I'm using to build AI-native organizations and products.

1. 1.If a knowledge, methodology, or tech stack is older than 3 years, it is obsolete until proven otherwise.
2. 2.Your codebase, docs, and meeting notes are not your backbone; your test case library is the only compounding asset.
3. 3.AI is completely, fundamentally stateless.
4. 4.We can accept AI mistakes as long as they do not kill the team before the next model upgrade.
5. 5.Software complexity must flatten: from deep vertical stacks to wide horizontal systems.
6. 6.The context window is the most critical computational resource every engineer must master.
7. 7.Plan-Act, Test-Code, and Doc-Code-Doc are the new working loops of engineering.
8. 8.The future of code is not abstraction but tiny, isolated, AI-readable units that stand on their own.
9. 9.AI will never solve the first mile or the last mile; those remain stubbornly human.
10. 10.AI-generated artifacts are not side effects; they are a new software modality and part of your engineering assets.
11. 11.The real power of AI IDEs and agents is not generation; it is ruthless, intelligent context selection.