Lazy Syllabus Planner: a local AI that tells you the least you need to do this week

Description and use

A local Python tool uses open LLMs via Ollama to extract assignment deadlines from syllabi, producing a weekly plan, calendar file, and morning note while keeping data private.

Problem

Students need to extract due dates from multiple syllabi without manually copying them, while keeping personal data private and avoiding cloud services.

Outcome

The final version correctly identified all 20 real deadlines across three sample syllabi, eliminated all hallucinated items, and produced a weekly plan and calendar file in 7–9 minutes on a 16 GB laptop.

Workflow

• Drop syllabus PDFs or Word files into a folder
• Run python planner.py syllabi to parse files
• Model outputs deadlines in a fixed JSON schema
• Code validates quotes and dates against PDFs
• Duplicates and hallucinations are filtered
• Start dates are calculated from effort ratings
• Outputs: plan.md, deadlines.ics, morning.txt

Evidence

A model on your own laptop finds every due date, then normal code works out the latest day you can start each thing.

Source

The final version found 20 of 20 real deadlines and 0 wrong items in about 7 to 9 minutes.

Source

No API keys, no accounts.

Source