jrklaus8 bakes Ontario's conduct rules into Mike

The Canada fork stops treating professional-responsibility rules as a footnote and writes them straight into how the assistant behaves.

compliancechat-ui

jrklaus8 has wired specific Law Society of Ontario rules into the assistant's core instructions. The competence rule is now cited by name, with a hard instruction never to fabricate case law. A second addition tells the model to refuse when someone tries to paste confidential or privileged client information into an unsecured prompt. Whether a language model reliably honours that refusal is its own question, but the obligation is now written down rather than assumed.

The fork also adds a dedicated compliance panel alongside the chat, and stamps plain "AS IS" no-warranty notices across the readme, the opening screen, and the chat footer. Those notices don't change anyone's actual liability, but they set expectations for a tool built on open-source code.

So what Worth a look for anyone weighing a Mike deployment inside a Canadian - specifically Ontario - law firm, where mapping software behaviour to bar rules is the difference between usable and unshippable.

View this fork on GitHub →

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

Commits in this thread

2 commits from jrklaus8/mike-Canada, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date
6749e429 feat: Integrate LSO AI Compliance framework (Competence, Supervision, Transparency) MikeOSS Bot 2026-05-22 ↗ GitHub
0398d2c7 docs: Add open source AS IS and use at your own risk disclaimers MikeOSS Bot 2026-05-22 ↗ 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-545.md from inside the repo you want the changes in.

⬇ Download capture-thread-545.md