← All work

Logistics · AI Document Intelligence

Sample writeup

Three-day BOL backlogs cleared the same day.

A mid-market US freight broker was three days behind on BOL and invoice processing, every day. Errors cost real money downstream. We embedded with ops, deployed a document pipeline against their real worst-case docs, and turned a 3-day backlog into same-day processing.

Client
Anonymized · US Freight Broker
Industry
Freight & Logistics
Region
United States
Duration
10 weeks

The challenge

12 people processing BOLs, invoices, and rate confs by hand across emails, PDFs, EDI, and photos from drivers. Error rate around 3%, costly when the average load is $1,800 and a single mistyped invoice number delayed payment by 2 weeks.

The approach

Identify. Build. Adopt.

01

Identify

Week one: 'send us your 50 worst documents.' We benchmarked the pipeline against their actual edge cases (handwritten amendments, blurry trailer-cab photos, multi-page rate confs) and showed the math: 1,400 hours/year of pure data entry, with measurable error cost.

02

Build

Multimodal extraction (Claude/Gemini vision) + specialized OCR for the harder docs, structured to a Pydantic schema, validated against the TMS, queued for human review when confidence dropped below threshold. Integrated straight into their existing ops dashboard so the team never left their workflow.

03

Adopt

Two-week parallel run. Every doc went through both the pipeline and a human; we logged every disagreement and tuned. By week 8, the team trusted the queue enough to flip the default from 'review every doc' to 'review only the flagged ones.'

Outcomes

What changed, measurably.

95%
Less manual entry
3 days → same day
BOL backlog cleared
0.3%
Error rate, down from 3%
~1,300 hrs/yr
Returned to ops team
Services used
AI Document IntelligenceAI Workflow Automation
We stopped chasing missing data and started running the brokerage again. The pipeline catches what we used to catch on a good day.
VP, Operations
US Freight Broker

Got a similar leak?

30 minutes with the founders. Bring us the workflow that hurts most. We'll cost the leak live and tell you whether the same playbook deploys here.