All Prompts

Build the synthetic data generation plan for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the responsible-AI review checklist for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the red team plan for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the rag quality evaluation plan for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the prompt-injection threat review for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the prompt-feature specification for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the prompt spec writer for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the prompt engineering workshop builder for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the prompt A/B test designer for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the model-selection trade-off matrix for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the model selection memo for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the model drift monitoring plan for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the llm-as-judge eval setup for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the llm cost vs quality analysis for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the human-in-the-loop flow design for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the hallucination mitigation strategy for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the golden test-set builder for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the fine-tune vs prompt vs rag memo for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the eval-driven model upgrade check for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the eval spec generator for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the eval set & rubric designer for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the eval dataset curator for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the cost per query audit for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the confidence & uncertainty UX spec for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.

Build the bias & fairness audit prompt for AI product work, covering eval criteria, failure modes, test data, safety risks, model behavior, and release decisions.