Use cases · Supply chain & logistics
Read, validate, and clear shipping documents in any language.
bem reads bills of lading, rate confirmations, customs forms, manifests, and packing lists, validates them against your rules, and returns a booking decision with the reasoning.
65%
Faster paper invoice processing, with accuracy held. Fleetio
Inputs it reads
- Bills of lading
- Rate confirmations
- Customs forms
- Manifests
- Packing lists
- Cargo video
From input to decision, in one workflow.
A bill of lading goes in. Your rules run against the extracted fields. A booking decision comes back with its reasoning.
Input
- DOCBill of ladingScanned PDF, with French customs text
Components
- 01ParseReads the scan into 37 sections in 22.2 seconds.
- 02ClassifyIdentifies it as a bill of lading in 2.9 seconds.
- 03ExtractTyped fields in 14.6 seconds. Container NIDU 180101-5 at 0.99.
- 04EnrichMatches the carrier against your reference data in 0.5 seconds.
- 05DecideApplies your party, container, and weight rules.
- 06SendDelivers the record to your booking system.
Decision
Clear for booking
Consignee and notify party match. Container and seal numbers are present. Gross weight of 28,000 kg is under the 30,480 kg limit.
confidence 0.98
The decisions your operations team makes today.
Each one is a rule you write. bem applies it to every document and shows its reasoning.
- 01
Clear for booking
Parties match, identifiers are present, and weights are within limits.
- 02
Hold for a missing document
A shipment missing a required document is held with the gap listed.
- 03
Flag a mismatch
A weight, party, or port that disagrees across documents is flagged with both values.
Why operations can trust the record.
- 01
Multilingual by default
Documents in one language with text in another still come back as one typed record.
- 02
A score on every field
Low-confidence fields go to a person instead of into your system of record.
- 03
An audit trail on every run
Open any record and trace it back to the page it came from.
How supply chain & logistics teams automate it.
- Best AI to process freight and logistics documentsExtend, Reducto, ABBYY, Nanonets, and Docsumo are all credible, and the right choice depends on which documents you run and what a wrong field costs.
- How to automate document data entry into your TMSPut a schema-enforced extraction layer in front of the TMS: every rate confirmation, BOL, or carrier invoice becomes typed JSON matching your TMS ingestion fields, delivered by webhook, with per-field confidence scores routing uncertain values to review.
- How to automate freight audit and payment with AIExtract the rate confirmation, bill of lading, and carrier invoice into one typed schema, let software reconcile them line by line, and pay only when they agree.
- The best AI for extracting data from bills of ladingFor most teams the shortlist is six: ABBYY Vantage, Rossum, Nanonets, and Docsumo offer pre-trained BOL models an operations team can run; Reducto parses ugly scans and handwriting into typed JSON; bem returns schema-enforced, confidence-scored records your TMS ingests without cleanup.
Clear your first shipment.
The first 100 function calls are free. Pricing is per task, not per token or page. Pay as you go, with no lock-in.