Unlike traditional software where problems are solved by debugging code, improving AI systems is an organic process. Getting from an 80% effective prototype to a 99% production-ready system requires a new development loop focused on collecting user feedback and signals to retrain the model.

Unlike traditional software development, AI-native founders avoid long-term, deterministic roadmaps. They recognize that AI capabilities change so rapidly that the most effective strategy is to maximize what's possible *now* with fast iteration cycles, rather than planning for a speculative future.

Treating AI evaluation like a final exam is a mistake. For critical enterprise systems, evaluations should be embedded at every step of an agent's workflow (e.g., after planning, before action). This is akin to unit testing in classic software development and is essential for building trustworthy, production-ready agents.

Frame AI agent development like training an intern. Initially, they need clear instructions, access to tools, and your specific systems. They won't be perfect at first, but with iterative feedback and training ('progress over perfection'), they can evolve to handle complex tasks autonomously.

The true building block of an AI feature is the "agent"—a combination of the model, system prompts, tool descriptions, and feedback loops. Swapping an LLM is not a simple drop-in replacement; it breaks the agent's behavior and requires re-engineering the entire system around it.

The traditional product management workflow (spec -> engineer build) is obsolete. The modern AI PM uses agentic tools to build, test, and iterate on the initial product, handing a working, validated prototype to engineering for productionalization.

Instead of codebases becoming harder to manage over time, use an AI agent to create a "compounding engineering" system. Codify learnings from each feature build—successful plans, bug fixes, tests—back into the agent's prompts and tools, making future development faster and easier.

In AI, low prototyping costs and customer uncertainty make the traditional research-first PM model obsolete. The new approach is to build a prototype quickly, show it to customers to discover possibilities, and then iterate based on their reactions, effectively building the solution before the problem is fully defined.

Building a functional AI agent is just the starting point. The real work lies in developing a set of evaluations ("evals") to test if the agent consistently behaves as expected. Without quantifying failures and successes against a standard, you're just guessing, not iteratively improving the agent's performance.