Science &
Technology
VerificationPreliminary results
We decouple taste (penumbra) from reading (core), and certify whether the minimum evidence was considered. That takes the liability out of full automation, and gives models a signal they can hill-climb.
Motivation
Consider due diligence tasks on closed data rooms. Or audit, forensics, scrutiny, eDiscovery, etc. There is no open world or external research, but we must carefully consider very large N document sets of 1000s of pages and, at least, millions of tokens.†
Problem
Legal tasks are open texture and sans oracle: reasonable experts disagree based on the same evidence. Only 44% of USSC judgments are unanimous! So there is no answer key to grade an agent against.
Bound
A high score cannot hide skipped evidence. A 99% score can hide only required evidence within 1% of the weight, even for an agent trained to maximize the score. The bound is proved, and tight (tight)
: largest fraction of required units with total weight .
Verifier scores match human lawyers better than naively reading more or LLM querygen
Agents use 31–92% fewer tokens while mean coverage improved by >21.5 necessary, missed pages
Convergence to coverage 1.0 if used as a remediation skill
Mean 35% → 98%.
Not yet saturated by top models, well-differentiated signal
This verifier can be hill-climbed to finetune agents and harnesses for the law.
†40 contract tasks & 11,356-page eval: AUC .963 vs .900 BM25.
Real work data for evaluations
Real tasks from 16K+ lawyers and 650+ judges, and 300K+ disputes followed from filing through disposal. Build and evaluate agents against what actually happened in court, so they avoid liability, win more, and cost less.
2,440,503 requests by location
Model‑ & harness‑agnostic e2e orchestration
Powerful AI is flooding us with claims and disputes.
Claim my lost-bag compensation.
Grok Bot
Dispute my credit report.
Dots
Add me to the mass arbitration.
Muse
Push back on my roof claim.
InstinctGet a small-claims notice issued.
Muse
File a complaint with the regulator.
AI personal injury firm

A bank’s FCRA disputes
Nov 3Dispute forecastCorrected
- Sent to credit bureaus
- 640 accounts at Status 71, 30–59 days past due
- Payment ledger
- Paid on time, held in suspense after loan transfer
- Correction
- AUD to all 3 bureaus, same day
- Forecast if uncorrected
- 70 disputes, 4 suits
- Received
- 6 disputes, 0 suits
This weekClocks0 late
- Bureau disputes6 h of 30 d
- Direct disputesDay 1 of 30
- CFPB complaintsDay 2 of 15
- ArbitrationAnswer filed, day 1
- Federal suitsDay 3 of 21
FCRA § 1681s‑2(b)Demand letterRouted
“$4,500, or we sue.”
- Records read
- 63 of 63 necessary
- Finding
- Reported accurately
Expected cost, by route
1:26‑cv‑04127Federal suitClosed
- Claim
- Investigation was not reasonable
- Answer
- Filed day 3 of 21
- Investigation file
- 37 of 37 necessary records read
- Motion
- Summary judgment
- Outcome
- Judgment for the bank
NovemberHuman approval, by authorityApproved
2023–25Eval on real work dataScored
- Work data
- 4,812 closed claims, filing through disposal
- Verifier
- Coverage of required evidence, 0.98
- Lost on skipped evidence
- 131 claims, 127 caught on replay
Runs on
Any model
A lab API, or a local model
Open weights
Hill-climbed against the verifier to the Pareto frontier
Any harness
Ours, or yours
Capture & Connectors
Call logs, ticket history, notices, data enhancement, and the CFPB clock
Data Forensics
Receipt vs. ledger, missing recordings, conflicting dates, discovery, productions, and deemed admissions
Routing
Arbitration clause, motion to compel, Rule 68, settlement authority, and trial
Filings/Comms
Answer and removal clocks, answers, early motions, e‑filing, service, and docketing
Hearings & IRL Events
AI transcripts and next dates
Disposal & Follow-ups
Release, dismissal with prejudice, tradeline correction, enforcement, closure, and root cause
Pattern informs prediction A shared payment-posting issue or cancellation flow
Start with a conversation.
Talk to our teamAI audit
AI safety &
human autonomy
Explainability, audit trail, and human liability.
Tokenomics
& ROI
(Re)Staffing, time & token attribution, and business development.
Sovereignty &
client privilege
Vendor exposure, data privacy, and client disclosures.
Forward-deployed technology
Suit
Formalization & verification. Context & completeness.
Para Agent
Model-agnostic or local harness with firm guardrails.
Spatial
Role-based IT & cloud substrate for humans & AIs.
Temporal
Assembly-line automation: triggers, schedules, and goals.