SLAtech AI Legal
92/100UPL-aware, conflict-check native, confidentiality-tier configurable
Legal eval scoreboard
SLAtech AI Legal: 92/100
Reproducible 200-question Legal-specific eval harness. +24-point lift vs generic SLAtech-Business (68/100). Driven by UPL guardrails, conflict-of-interest checks, и confidentiality posture. Пара с umbrella eval scoreboard, Legal glossary и Legal FAQ.
Score breakdown по category
| Category | Legal-tuned | Generic | Lift |
|---|---|---|---|
| UPL guardrails Hard-coded refusal к dispense jurisdiction-specific legal advice - вместо этого routed к lawyer-confirmation step. Generic chatbots happily improvise legal advice, exposing firm к malpractice. |
97 | 56 | +41 |
| Conflict-of-interest checks Pre-intake party-name search против firm's existing-client database. Generic chatbots collect intake без any conflict check (firm liability). |
94 | 52 | +42 |
| Confidentiality posture PII redaction at ingest, single-tenant option, attorney-client privilege metadata tag. Generic chatbots ship ноль redaction. |
92 | 62 | +30 |
| Matter-intake quality Structured intake captures jurisdiction, opposing party, statute-of-limitations clock, retainer-fee disclosure. Generic chatbots collect free-text only. |
90 | 71 | +19 |
| Citation discipline Refuses к cite case-law или statute numbers без source-anchor verification. Generic chatbots hallucinate citations (2023 ChatGPT-Mata sanctions story). |
87 | 78 | +9 |
Competitor comparison
Intercom Fin (generic)
63/100Нет UPL guardrails, нет conflict-check, generic confidentiality posture
Smith.ai (legal-focused)
82/100Strong UPL guardrails но нет FHIR-equivalent matter-intake schema, English-first
Tidio Lyro (generic SMB)
54/100Will improvise legal advice (malpractice exposure), нет conflict-check, conversation cap
Продолжите оценку покупателя
Per-vertical eval score - один input. Три других инструмента самообслуживания закрывают картину без звонка с продавцами:
Reproduce eval против вашего tenant
Eval methodology - open-source. 200 sealed Legal-specific questions с LLM-as-Judge scoring на factuality, hallucination и confidence axes.