pdombkins turns Mike into a managed law-school cohort platform

This fork adds the practical controls needed to run shared legal-AI work across a class without losing track of access or spend.

workflowinfrastructure

pdombkins is building beyond a collaboration portal toward a course-ready workspace, with the strongest ideas being portable to any managed deployment.

  • Student groups with bulk invitations, so a cohort can be set up without adding people one at a time.
  • Per-project query budgets and a visible warning, helping organisers cap AI usage costs before they become a surprise.
  • Shared lists with CSV import and export, making it easier to bring structured class material in and take it back out.
  • Initial teaching-case materials for a law course, alongside the platform work.

The same release also prepares the service for broader browser access and deployment, but the cohort and budget controls are the substantive move.

So what Law schools, legal-ops teams and anyone running metered shared AI work should care because this is the operational layer that makes a pilot governable.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

1 commit from pdombkins/rose_lawyer, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date
4a0c0b2c Deploy config, student groups + bulk invite, multi-origin CORS; lists/usage/budget features; teaching content Peter Dombkins 2026-07-23 ↗ GitHub

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-935.md from inside the repo you want the changes in.

⬇ Download capture-thread-935.md