A teammate has attached a screenshot or PDF and assumes the model will automatically know whether to compare it, extract from it, or diagnose it. “I already dumped the screenshot in there. The model should be able to tell me what matters.” “The screenshot gives the model evidence, but not the job. We still need to say whether we want comparison, diagnosis, extraction, or a recommendation, and what standard the answer should use. Otherwise it usually gives generic commentary instead of the decision we actually need.” This response is strong because it does not argue abstractly about prompting. It names…
Read the full lesson
Sign up free: one personalized lesson every day, matched to your role and goals.
Already have an account? Sign in