Role-based agents, supervised by your staff. Every agent reports to a human office, works at the autonomy level you set, and publishes what it never does right on its profile.
A clerk enters one case update, on the record. Scribe drafts the notice in three languages, Ledger adjusts the payment plan, and Guide already has the answer when the person checks the portal. As the in-development agents ship, the same update reaches further: Docket adjusts the calendar and flags the conflict it creates, Compass tells the supervising officer whose person’s date just moved, Vantage shows the whole thing moving. One update, every action attributed, before anyone has to ask.
A continuance was granted at 9:14. By 9:15 her agents had the cascade ready: the new date checked against every calendar, notices in three languages, the payment plan moved, the portal answer updated. She reviews it, approves once, and seven systems agree. The person standing at her counter gets her full attention.
The department line was answered before she reached the building, and last night’s check-in reminders went out in each person’s language, every one on the record. The hour she used to lose to callbacks goes to the two people who actually need her today.
He asks what he owes and what happens next. The answer comes in his language, in plain words, with a payment plan he can actually keep. No lines, no legalese, no guessing. He leaves knowing exactly what to do.
She sees her court the way a pilot sees a cockpit: workloads, backlogs, and bottlenecks, live. When she asks why Thursday is jammed, the answer arrives with its sources attached.
Voice Agent
The phones never stop. Relay answers the routine calls so your staff can stop.
Meet Relay
Public Assistant
A self-represented litigant in the lobby gets the clarity a seasoned attorney would: what they owe, when to appear, what happens next, in their language, in plain words.
Meet Guide
Documents & Notices
A case update entered once becomes a notice in three languages, a calendar change, and an answer waiting in the portal, before anyone has to ask.
Meet Scribe
Payments
Fines and fees stop going uncollected for lack of follow-up, and paying the court becomes as clear as any other bill.
Meet Ledger
Three agents are being built now, with partner agencies, and ship when they meet the bar the rest of the roster already clears. Their profiles say exactly what they will and will never do, so your agency can plan for them honestly.
The development partner program is how they get built: partner agencies shape the workflows, test with real caseloads under their own governance, and go live first. Ask about it in a demo. When an agent ships, it ships with references, not promises.
Clerk Copilot
A clerk doesn’t navigate seven systems. She says “prepare the warrant packet for my signature” or “show me tomorrow’s conflicts,” and the stitching is already done when she looks up.
Meet Docket
Supervision
A probation officer starts her morning with her caseload already triaged, freeing her hours for the conversations that actually change outcomes.
Meet Compass
Court Cockpit
A presiding judge sees her court the way a pilot sees a cockpit: workloads, backlogs, and bottlenecks visible in real time instead of reconstructed quarterly.
Meet Vantage
Most agencies start with Relay, the voice agent: the pain is universal, and a thirty-minute demo shows it working in your context. Connect what you have, keep your staff in control, and add the next role when the results make the case.
Not sure where to start?Get an AI readiness plan
GuideAI assistant
Reports to the eCourt AI team
Always labeled AI. Unsure means handed to a person.