In an era of ephemeral apps, storing core information in a basic, text-based format like Markdown is the ultimate future-proofing strategy. It ensures data remains portable and accessible to any future AI model or application, similar to how plain-text HTTP drove web adoption.

Instead of chasing the latest hyped AI model, focus on building modular, system-based workflows. This allows you to easily plug in new, better models as they are released, instantly upgrading your capabilities without having to start over.

A key pillar of human-centric AI is ensuring data is "future-proof." Because models are trained on historical data, they can quickly become irrelevant or harmful as market conditions change. This requires a proactive strategy to prevent model decay, not just reactive fixes after failures occur.

Contrary to the "data is the new oil" axiom, historical oncology data has a short shelf-life. The continuous evolution of treatments and data-generation technologies means recent, contextual data is far more valuable for training AI models than large, outdated archives.

Instead of embedding data directly into your prompt, instruct the AI to save it as a separate file (e.g., data.json). This decouples design from content, allowing you to instantly generate new prototype variations simply by swapping the data file.

Relying on chat history for an AI's memory is fragile. A more robust method is to have the AI serialize key learnings into an external, structured file system (like an Obsidian vault). This creates inspectable, editable, and reusable artifacts that can outlive any single conversation thread.

Contrary to the goal of perfect data retention, 'machine unlearning' is becoming a critical capability. The ability for an AI to forget is essential for privacy (removing user data), correcting biases from flawed training data, and adapting to new information, mirroring a core, beneficial aspect of human cognition.

Your custom-built workflows will become obsolete as general AI capabilities improve. Proactively run a scheduled process where your AI analyzes your systems to find over-engineered parts that can be replaced by its own improving, native intelligence, preventing system stagnation.

Building on AI requires creating custom infrastructure to fill performance gaps. As underlying models improve, founders must be prepared to delete this now-redundant code and upgrade their product vision to tackle the next set of challenges at the new frontier. This cycle of building and deleting is key to staying innovative.