RagLeapShort answer: run RagLeap Core, load the information your front desk answers from today, and use the built-in legal_intake role, which the code treats as a sensitive domain. It answers routine questions and collects intake details. It is not a lawyer, gives no legal advice, and this page is not legal advice. The steps are in the general setup guide.
Which roles apply?
legal_intake and compliance_officer are among the built-in sensitive-domain roles in the code (sensitivity.py at v0.11.0): they are forced to semi or off autonomy and get a reasoning mode and a grounding check, and the README says sensitive roles always need approval. immigration_intake, secretary and support also exist among the 46 roles.
What would you upload?
Practice-area descriptions, the fees you publish, how to book a consultation, office hours and locations, and your intake checklist. Use the Documents tab (PDF, Word and other files, or a public web page). Do not upload client files unless you have decided that your setup, your provider and your professional rules allow it.
How do people reach it?
Through WhatsApp, Telegram, Discord or a voice line (Twilio). A website chat widget is planned, not built. Language detection runs across every channel; short messages in closely related languages can be misdetected.
What should you check first?
- Not legal advice. No accuracy claim is made. Do not let the assistant advise, and keep it at
offorsemi. - Confidentiality. Check your professional-conduct rules and your AI provider terms before any client information goes through a provider.
- Autonomy is
offby default;semiasks before acting;fullis opt-in. Read real conversations before going live. - Your documents and each conversation go to the AI provider you configure. A local Ollama model keeps those steps on your machine, but local models on a CPU are slower and less accurate than Gemini.
- Single-tenant: one deployment, one business, one document set. Named users and roles arrived in v0.12.0: four roles, personal keys and an audit log of who made each state-changing request (updated 2026-10-29: this page said “No named users or roles yet”). No single sign-on or multi-factor sign-in, and no independent security review yet.
- No results for this field are claimed, and no compliance certification. Test with your own documents and questions.
Sources
The v0.11.0 README, defaults.py and the AI employees documentation.