A voice agent that is actually built for law: what jurisdiction-aware has to mean
Most voice agents treat jurisdiction as a language setting. For legal intake it has to govern what the agent asks, what it computes and what it refuses to say.
Open Bar at mid-year: housing, employment and immigration triage, by the numbers
Six months of Open Bar intake data: 48,000 conversations, three categories that account for most of them, and the parts of the platform that clinics do not touch.
One client, one vault: per-client memory for AI Interview
AI Interview now keeps what it learns about a client in a vault that only that client’s sessions can open. Returning callers resume where they left off. Firms can seal or purge a vault outright.
The empathy layer: what we learned building Interview with trauma-informed clinicians
What should a voice agent do when the caller starts crying? We spent six months with three clinicians and 140 mock intakes finding out. The answers were mostly about pacing and consent.
Conflict checks before the call ends: how Interview cross-references a firm’s matter database
A prospective client names a counterparty at minute four of an intake call. By minute five the firm knows whether that name appears in its own matter history. How the check works, and how to set it up.
Limitation-period math is a date problem, not a law problem
Knowing the limitation rule is the easy part. Applying it to a client’s account requires a trigger date, a counting convention and a set of tolling conditions. Here is how Interview does the arithmetic, and where it stops.
AI Interview is generally available: the first conversation, handled with care
AI Interview moves from limited preview to general availability. It conducts a first client-intake conversation, by voice or text, in 38 languages, and produces a structured brief with limitation dates and a conflict check.