pdombkins gives each project its own legal context

A new admin setting lets each project tell the AI who it is working for before the conversation starts.

multi-tenantworkflow

Rather than forcing every matter through one generic set of instructions, pdombkins has added a place for an administrator to record organisation-specific context for each project. That context is then included when the AI responds in chat.

In practice, this could let a firm or legal team shape the assistant around its own working environment without hard-coding separate versions of the product. The change is deliberately controlled by an administrator, not supplied casually by an end user.

It is a small move, but an important one: useful legal AI needs to understand the setting around a matter, not just the words in a prompt.

So what Legal teams exploring shared AI tools should care because this makes project-level tailoring more practical without turning every deployment into a bespoke build.

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
39e10f52 Per-project organisational context: admin editor + prompt injection Peter Dombkins 2026-07-24 ↗ 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-944.md from inside the repo you want the changes in.

⬇ Download capture-thread-944.md