Private beta · By invitation

The federal docket,
on speaking terms.

APEX schedules hearings, drafts decisions, and runs case research — by conversation. Built for administrative law judges, case managers, and intake staff. Thirty specialized AI tools. Every action audited. Every citation grounded.

Built for the federal docket · Audit log of record · Zero fabricated citations
apex / Case 2026-000042 · Smith v. State Agency
Schedule a pre-trial — first available with the assigned ALJ.
🔎 find_available_hearing_slots

Checking Judge Patel's calendar over the next 14 days. Predicting hearing duration from comparable cases…

#DateTimeRoomScore
1Tue May 2609:00–10:303A0.92
2Wed May 2714:00–15:303A0.88
3Thu May 2809:00–10:302B0.85
⚠ Action requires confirmation
Schedule PRE_TRIAL on Tue May 26, 09:00 with Judge Patel
in Courtroom 3A · est. 90 min · confidence 0.92.
Every mutation goes through an action card. The AI proposes — you confirm.
01

Conversational

Ask APEX to schedule, search, draft, or research — in plain English. It chooses the right tool, fills in the gaps, and proposes the action before doing it.

02

Compliant

Every AI invocation is logged with the calling user, the tool, the parameters, and the outcome. Citations are grounded in real knowledge-base entries. Fabricated citations are forbidden by policy and verified by the system.

03

Calibrated

Mutations require user confirmation. Tools are filtered by role. The model knows what it doesn't know — and says so plainly.

The conversation, end to end

From "first available" to filed in three confirmations.

APEX doesn't dump a chatbot in front of your existing system. It orchestrates the intelligent agents that already live in your case-management stack — scheduling, ALJ assignment, decision drafting — and routes through them with full audit trail.

Step 01

You ask.

Open a case. Type a question or an intent. No forms. No menus.

› what cases is Judge Blanda working?
Step 02

APEX selects the tool.

The model maps your intent to the right capability. Smart search, slot finder, decision drafter, cascade impact analyzer — thirty in all.

› smart_search → name-aware ALJ filter
Step 03

You confirm.

For anything mutating, APEX proposes — never decides. You see the parameters, the confidence score, the chosen ALJ. Click confirm or cancel.

› ⚠ Action card → ✓ confirmed → logged forever
Capabilities

Thirty tools, one conversation.

Each tool is purpose-built, role-scoped, and audited. Selected highlights below — the full catalog ships in the demo.

🗓

Intelligent scheduling

Score-ranked slots across ALJ availability, courtroom conflicts, interpreter needs, and hearing-format constraints. Predicts duration from your historical record.

⚖️

ALJ assignment

Ranks judges by workload, jurisdiction, specialization, and COI. Surfaces a justification with every recommendation.

🎭

Hearing rehearsal

Generates a realistic mock transcript grounded in the case facts — for counsel prep or judicial rehearsal. Stays inside the record. Never invents testimony.

✍️

Decision drafting

Drafts decisions from case context, prior filings, and applicable precedent. Every citation traces to a real entry. Every claim shows its source.

🔍

Grounded research

Synthesizes legal memos from the federal knowledge base. Vector + symbolic search. Refuses to answer when the corpus is silent.

Cascade-impact analysis

Before you reschedule a hearing, APEX shows every downstream hearing it would affect, every conflict it would create, and every buffer it would violate.

📊

Workload balance

Live fairness score across your bench. Spot overloaded judges before the next assignment.

🧠

Case memory

Long-term observations the AI remembers between conversations — pinnable, dismissable, audited.

🚨

Killswitch

One toggle disables every AI capability across the system. For incidents, audits, or maintenance windows.

Plus: deadline alerts · capacity forecasting · classification pipelines · precedent comparison · personal task capture · feedback loop with structured categories.
The product, not a render

What it actually looks like.

Four shots from the running system. Each one is the actual UI — not a mockup, not a marketing render. The case data is from a live demo deployment.

APEX AI shell — conversational interface with a real case-management query, tool chips above the assistant turn, and a citation panel on the right.
01 Conversational hero. Ask "what cases is Judge Blanda working?" — APEX picks smart_search, runs it with the name-aware ALJ filter, and returns the workload summary with live citations. Right inspector shows what sources were consulted.
ALJ scheduling calendar with single-ALJ, multi-ALJ, and batch-schedule modes plus AI Insights.
02 Intelligent scheduling. Single-ALJ, multi-ALJ, and batch modes. The "AI Insights" pane surfaces cascade impact, predicted duration, and workload balance before you book.
Case list view with status, priority, jurisdiction, and assigned-ALJ filters; sortable columns and per-row priority badges.
03 The traditional surface, when you want it. APEX is AI-native — but the table view, the filters, the badges, the "Switch to Traditional" link are all there for the days you want a list, not a conversation.
Agent audit log: read-only table of every AI action with agent username, action type, entity, status, duration, and timestamp.
04 Read-only for compliance. Every AI action — classification, scheduling, cancellation, decision draft, memory write — captured before it runs. Immutable. Exportable. Federal-grade.
Compliance is not a feature.

Built for the audit, not around it.

APEX writes the audit log of record. Every AI action, every parameter, every outcome — captured before the action even runs. Independently queryable. Exportable.

4
layers of access control
view, role-scoped tool catalog, per-execute Jmix permission, row-level (optional)
0
fabricated citations
no-fabrication policy enforced at the model prompt level and verified post-hoc
100%
mutating-tool confirmation
no AI mutation runs without an explicit human approve. ever.
cap_AgentAuditLog read-only · immutable · federal-grade
created_atagentactionentitystatus
2026-05-20 09:14:02j.patel@oahSCHEDULE_HEARINGHearingOK
2026-05-20 09:13:48j.patel@oahFIND_AVAILABLE_SLOTSCaseOK
2026-05-20 09:13:12m.kim@oahGENERATE_DECISION_DRAFTDecisionOK
2026-05-20 09:12:55s.rivera@oahRESCHEDULE_HEARINGHearingOK
2026-05-20 09:11:30l.chen@oahCLASSIFY_DOCUMENTDocumentOK
2026-05-20 09:10:18j.doe@oahCANCEL_HEARINGHearingDENIED
2026-05-20 09:09:55m.kim@oahWRITE_CASE_MEMORYCaseMemoryOK
Live, on the demo system. Every row is real.
An honest read on AI in your stack

The model is not your judge. It's your fastest clerk.

APEX does not replace decision-making. It removes the friction between you and the work that only you can do. When the model isn't certain, it asks. When the corpus doesn't support an answer, it says so. When you reject a proposal, the system learns — structurally — through the feedback loop.

The kill switch exists. The audit trail is non-negotiable. Mutations require your explicit hand. We built it this way because federal docket work demands it.

Private beta

By invitation. For offices, not individuals.

APEX is in closed beta with a small number of administrative law tribunals. If you run a docket and want to evaluate it for your office, write us. We'll respond personally.

✓ Thank you. We respond to every request within two business days.