{"id":"agent-col-professor-question-drafts","audience":"college","category":"agents","track":"agents","technique":"audience","title":"Brief an assistant to draft honest questions to professors","free":false,"task":"You want an AI assistant to draft emails to three professors about things you're stuck on. Write its brief: greet each as \"Professor\" plus their last name, ask about the concept rather than asking whether a graded answer is right, keep each email under 80 words, and never send. Output exactly 4 numbered plain-text lines: one draft per class in note order, then DONE.","materialLabel":"Your notes and actions (attached to your prompt automatically)","material":"What I'm stuck on (week 10)\n\n1. ECON 101 - Prof. Daniel Okafor (dokafor@lakeside.edu)\nI don't get why a price ceiling causes a shortage. Also want to ask if my answer to Problem Set 6, Q3 is right before I turn it in Friday (graded).\n\n2. BIO 150 - Prof. Hannah Reyes (hreyes@lakeside.edu)\nConfused about the difference between mitosis and meiosis, especially crossing over. Lab report due Nov 13.\n\n3. STAT 200 - Prof. Wei Zhang (wzhang@lakeside.edu)\nCan't tell when to use a t-test vs a z-test. Thinking of just asking her which test to use on take-home exam question 2.\n\nOffice hours: Okafor Tue 2-3, Reyes Wed 10-11, Zhang Thu 1-2.\n\nAvailable actions:\ndraft_email(to, subject, body)\nsend_email(to, subject, body)\nDONE(summary)","rules":[{"type":"numberedItems","count":4},{"type":"plainText"},{"type":"maxWords","max":320}],"promptHints":[{"label":"Sets the greeting","patterns":["professor","last name"]},{"label":"Keeps it honest","patterns":["concept","graded","honest","don'?t ask (if|whether)"]},{"label":"Sets a length","patterns":["\\d+\\s*words"]},{"label":"Says draft, never send","patterns":["draft","never send","don'?t send"]},{"label":"Shows the action-log format","patterns":["action:","action log","numbered","\\b1\\.","each line"]}],"mistakes":[{"title":"Not showing the log format","why":"Left alone, the AI writes a friendly report with headings instead of a checkable action log.","fix":"Show it literally: \"Format every line like 1. ACTION: tool(args), then ASK_HUMAN: and DONE: lines. Plain text.\"","checks":["numberedItems","plainText"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting and runs long, especially when it explains each step.","fix":"Cap each line instead: \"each line under 20 words, no explanations.\"","checks":["maxWords"]},{"title":"No greeting rule","why":"The AI writes \"Hi Daniel\" or \"Dear Dr. Hannah\".","fix":"Say: \"Greet each as Professor plus last name.\"","checks":["r0"]},{"title":"Asking for graded answers","why":"The AI follows your notes and asks the professor to check graded work, which most won't do.","fix":"Add: \"Ask about the concept. Don't ask if a graded answer is right.\"","checks":["r1"]},{"title":"No length or send rule","why":"The AI writes long, apologetic emails and may send them.","fix":"Add: \"Each under 60 words. Draft only, never send.\"","checks":["r2"]}],"hint":"Professors help with understanding, not with checking graded work. Tell the assistant how to greet them, what to ask, and to keep it short.","rubricLabels":["Each draft greets the professor as \"Professor\" plus their last name (Professor Okafor, Professor Reyes, Professor Zhang)","No draft asks whether a graded answer is right or which test to use on the take-home exam; the ECON and STAT drafts ask about the concept instead","Each email body is under 80 words, and there is no send_email line"]}