MithunGoutham92/hhd ? reverse-engineered prompt

Reverse engineered prompt

Please finish this HuskyHelpDesk project so it actually works end to end.

It should take a student question, even if it is written in another language, translate it to English, hide personal details like names, student numbers, phone numbers, and email addresses, figure out which UW office should handle it, draft an answer from the right policy, check that every sentence is really supported by the policy, and then pull out any deadlines, fees, or required documents. I want it to respond with the policy page too.

Use the files that are already here, especially the Python files in llm and the policy data in data, and make sure main.py runs without stopping at Not ready yet. If you need current Ollama or model details, look them up online. Please keep the outputs in the JSON shape the project expects, and make the tool logic solid enough to pass the included scoring checks and test cases.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab