This research note is part of an occasional series on AI benchmarking and cross-pollinated methods. The note addresses COSTAR prompting, working with different prompt configurations, modifying COSTAR to prioritise information targets, and the pitfalls of putting the horse before the cart.

This research note is part of an occasional series on AI benchmarking and cross-pollinated methods. The note addresses different prompt configurations for role-context-task (RCT prompting) and prime-persona-privacy-product-polish (5P prompting) tasks.