Amari AI

A large corpus of AI-drafted customs entries with their provenance trail, built across multiple leading brokerage teams: automated extraction from commercial invoices, packing lists, bills of lading and arrival notices, mapped through to ABI-ready draft entries with HTS classification and duty computed, each field traceable to its source document in an audit-ready trail - so the corpus pairs real source documents with the accepted structured entry. Layered on top is a continuously updated regulatory rule-mapping engine that tracks current tariff regimes including Section 122, IEEPA and Section 232 and documents how each regulatory change maps into entry logic, giving a dated history of rule application

Open buyer room →

Sample

Brickroad customers

Sample this dataset before you buy it.

Your sourcing agent asks Amari AI and files the sample in your catalog — private to you.

Start 7-day trialNothing is charged until the trial ends.

Coverage

Universe, instruments and categories.

Industry: Application SoftwareAir Freight & Logistics
Instruments: equities
Categories: Alternative

Dataset card

Type: not stated
Format: Multimodal - source documents (invoices, packing lists, bills of lading, arrival notices) paired with the structured ABI-ready entry records derived from them, plus a documented rule-mapping trail; integrates over email and ABI
Volume: Over 1 million customs entries automated, stated on the page - the strongest published volume anchor in this cohort. Each entry carries extracted document fields plus its structured output, so the effective training-record count is substantially higher than the entry count, plausibly tens of millions of document-to-field pairs. Brokerage tenant count and per-entry document volume are not published and should be confirmed
Users: N/A - no user count published; enterprise B2B sold to brokerage teams, with the page quantifying output in entries processed rather than users, and a 13-person seed-funded team implying a small number of large brokerage tenants
History: 2 years
Update frequency: not stated
Growth: Active / scaling - seed-funded with US$4.5M raised, 13 staff in San Francisco, over a million entries automated for leading brokerage teams, and regulatory coverage tracking live current tariff measures, indicating a growing deployment rather than a static install base
Launched: Est. 2024 (organisational record created late 2024; the claim of over a million entries automated since then implies an aggressive deployment pace from a recent launch)
Delivery: not stated
Entity mapping: not stated
Sample: not stated
Point-in-time: not stated
Licence: not stated

supplier index read from their site