Over time, prompts become long and complex, accumulating contradictions from multiple contributors. Chip Huyen suggests treating them like a codebase: use another AI to analyze the prompt for inconsistencies and "refactor" it for better performance and clarity.

While detailed prompts are useful, starting with simple, open-ended prompts can unlock more creative and strategic responses from AI models. Experimenting with different levels of prompt detail across various models often yields surprising and superior results.

While a multi-model approach—using the best AI for each specific task—is theoretically optimal, its practical implementation is difficult. A major roadblock is the need to create and maintain different optimized prompts for each model. This overhead leads users to default to a single, powerful model for simplicity.

Sophisticated model routers do more than route queries to the cheapest AI model. Palantir's Evolve tool also automatically optimizes prompts for the target model, a dual approach that can reduce token consumption by 60% and overall compute costs by up to 97% for specific tasks.

OpenAI favors "zero gradient" prompt optimization because serving thousands of unique, fine-tuned model snapshots is operationally very difficult. Prompt-based adjustments allow performance gains without the immense infrastructure burden, making it a more practical and scalable approach for both OpenAI and developers.

Integrating the latest foundation model is complex because new models can break prompt tuning built around the quirks of older versions. Serval has found that a new model's unpredictability can outweigh its intelligence, sometimes forcing them to downgrade to an older, more reliable model to ensure consistent behavior.

A practical hack to combat rising AI API costs is instructing models to respond with minimal, non-grammatical language. By using prompts like "did thing" instead of a full sentence, users can drastically reduce token consumption for a given task, directly lowering operational expenses.

The binary distinction between "reasoning" and "non-reasoning" models is becoming obsolete. The more critical metric is now "token efficiency"—a model's ability to use more tokens only when a task's difficulty requires it. This dynamic token usage is a key differentiator for cost and performance.

Good Star Labs found GPT-5's performance in their Diplomacy game skyrocketed with optimized prompts, moving it from the bottom to the top. This shows a model's inherent capability can be masked or revealed by its prompt, making "best model" a context-dependent title rather than an absolute one.