iGEN
Visit IGEN World Explore IGEN Expo
EXPLORE UPGRADE PLANS
BREAKING
Home ›› Technology ›› Ai ›› Llms ›› Wove AI Platform Cuts 2,000-Line Invoice Processing to 30 Seconds

Wove AI Platform Cuts 2,000-Line Invoice Processing to 30 Seconds

FreightWaves reported that Wove, an agentic orchestration platform for global trade, automates customs entry and invoice processing, handling 2,000-line documents in about 30 seconds. The company's tariff engine ingested a 431-page federal notice in about an hour, and its annual recurring revenue grew sevenfold over the past year.

iG
iGEN Editorial
August 6, 2026
Wove AI Platform Cuts 2,000-Line Invoice Processing to 30 Seconds

Keeping up with U.S. tariff changes and manual data entry has become a full-time job for freight forwarders and customs brokers, FreightWaves reported. Wove, an agentic orchestration platform for global trade, aims to change that: it can process a 2,000-line commercial invoice or packing list into CargoWise in roughly 30 seconds — work previously handled entirely by hand, according to FreightWaves.

2,000 Lines in 30 Seconds

FreightWaves reported that Wove's core automation platform handles shipment registration, customs entry writing, and one-off quote creation inside CargoWise. Jay Edlin, co-founder and CEO of Wove, told FreightWaves: "In this business, if you quote faster, you're probably going to win the business." Wove serves two primary customer segments: logistics service providers — freight forwarders and customs brokers — and, more recently, shippers through a tariff intelligence product.

The speed advantage matters because even a licensed customs broker can spend many hours parsing a document of that length, FreightWaves reported. Wove's platform converts that time into minutes for importers and their service providers.

Tariff Engine Built From Invoice Parsing

Wove's ingestion engine was originally built to handle unstructured data such as commercial invoices and packing lists, FreightWaves reported, and was repurposed for the U.S. Harmonized Tariff Schedule. According to FreightWaves, Wove has ingested more than 45 HTS revisions since last year, building a database of roughly 3.2 million rules covering Chapter 99 exclusions, inclusions, and effective dates. Edlin called it a "tariff time machine" that importers are using to run historical audits via API.

Edlin told FreightWaves that a recent Federal Register notice for new Section 301 tariffs — released about 12 hours before they went into effect — was 431 pages long. Wove's tariff engine ingested it in about an hour:

The Federal Register notice from last week for the new Section 301 tariffs, which came out about 12 hours before they went into effect, was 431 pages long. And with the technology that we have under the hood of our tariff engine, we were able to understand and ingest the 431-page notice in about an hour.

When a new Federal Register notice drops, an automated Slack alert triggers an AI agent to ingest the changes, with corrections from licensed customs broker partners turned around in minutes, according to FreightWaves.

From Weekend Side Project to Revenue

The free tariff calculator at tariffs.wove.com grew out of a weekend side project late last year, after a competitor — also a customs broker, according to Edlin — restricted access to its own free tool, FreightWaves reported. Wove's version drew thousands of users per week within a few months. The platform has since expanded into a premium tier and an API licensing business, with essentially zero customer acquisition cost, Edlin told FreightWaves.

Wove also white-labels its tariff data for customs brokers that want a branded calculator on their own websites, and offers a product catalog module allowing importers to bulk-upload SKU data and run real-time tariff exposure simulations, according to FreightWaves. Fortune 500 companies and academic researchers are among current users, Edlin said.

Business Results and Funding

FreightWaves reported that Wove grew its annual recurring revenue sevenfold over the past year. Edlin declined to disclose absolute ARR figures but confirmed the 7x growth. The company has raised less than $500,000 to date and remains largely bootstrapped, according to FreightWaves. The Chattanooga appearance marked Edlin's return since the 2022 F3 conference.

Metric Value
Invoice/packing list processing time ~30 seconds per 2,000 lines
Federal Register notice ingestion ~1 hour for 431 pages
HTS revisions ingested since last year 45+
Tariff rule database ~3.2 million rules
Total funding raised Less than $500,000
ARR growth over past year 7x

Human Expertise Remains

On the question of whether AI tools like Claude could replace customs brokers entirely, Edlin pushed back, according to FreightWaves. The important work, he said, is helping customers interpret the latest tariff updates — not manually entering line items into a TMS. For enterprise technology buyers, Wove's documented throughput gains demonstrate how AI orchestration can shift trade-compliance teams from repetitive data entry to strategic interpretation of tariff policy, while keeping licensed brokers in the loop for final judgement.


Sources: FreightWaves

Keep Reading

Recommended Stories

AI Promises Shorter Workweeks, but Tech Staff Report 90-Hour Weeks Technology

AI Promises Shorter Workweeks, but Tech Staff Report 90-Hour Weeks

Tech leaders have long promised AI will shorten working hours, but a BBC report found employees at OpenAI, Anthropic and Meta report weeks up to 90 hours. A former OpenAI employee said the firm never trialled the four-day week it recommended, and described a culture of weekend work and intense sprints.

August 10, 2026
AI Is Coming for Accounts Receivable’s Busywork, Not Its Jobs, Says FreightTech CEO Technology

AI Is Coming for Accounts Receivable’s Busywork, Not Its Jobs, Says FreightTech CEO

Stuut CEO Tarek Alaruri discusses how AI automates accounts receivable in freight brokerage, cutting overdue invoices by 40% by unifying previously siloed processes across the order-to-cash lifecycle.

July 22, 2026
LLM-Driven Stepwise Refinement Framework Promises Verifiable Hardware Generation Technology

LLM-Driven Stepwise Refinement Framework Promises Verifiable Hardware Generation

A new framework from researchers Li et al. combines large language models with formal methods to generate verifiable hardware designs. By applying stepwise transformation rules, the LLM agent produces correct register-transfer level (RTL) programs, addressing the reluctance of engineers to trust AI in high-stakes chip design.

June 20, 2026
Travel Disruption Is a Productivity Nightmare – AI Provides the Scalable Solution Technology

Travel Disruption Is a Productivity Nightmare – AI Provides the Scalable Solution

90% of business travelers deem corporate trips essential, yet disruptions like Storm Fern and the Heathrow fire cause massive manual workload. AI-powered agents can autonomously handle rebooking, decode airline waivers, and free human agents for complex cases, reducing operational costs.

June 16, 2026