Home What We Do How We Work Our Work Field Notes Our Story Get in Touch
Aerial view of shipping containers at a port, abstract and architectural, no text
Logistics — Document Processing

Freight document classification and routing

A regional logistics operator was processing 400–600 freight documents daily — bills of lading, CMRs, customs declarations — through a four-person team that spent most of their time on document type identification and initial routing. The workflow existed in email and a shared drive.

We mapped the classification logic over two days of sessions with the team, discovered that 73% of documents fell into six clear categories, and built a classification agent that routed with 94% accuracy on the real document set. The remaining 6% routes to a human review queue.

Result: 78% reduction in manual classification time. Team redirected to exception handling and client queries.
Abstract financial data visualization, minimal glowing nodes on dark background, no text
Fintech — Reconciliation

Invoice reconciliation agent for payment platform

A payment platform was reconciling invoices against transaction records manually at month-end — a process that took two finance team members most of their week and regularly caused delayed closes. The data lived in three systems with inconsistent naming conventions.

We built a reconciliation agent that normalises naming across systems, matches invoices to transactions with a configurable confidence threshold, and flags discrepancies for human review. The threshold was calibrated over three months of test runs against historical data before going live.

Result: Month-end close time reduced from 4–5 days to under 1 day. Discrepancy detection improved.
SaaS — Support Triage

Support ticket classification and first-response drafting

A B2B SaaS company with 200 enterprise clients was receiving 150–250 support tickets weekly, triaged manually by a two-person team before assignment. Response time was 8–12 hours for initial acknowledgement.

We built a triage agent that classifies by issue type, urgency, and account tier, then drafts an initial response for agent review and approval. The draft step was deliberate — the team wanted to maintain response quality, not automate it away. Approval takes 30–90 seconds per ticket.

Result: Initial response time down to under 2 hours. Support team handles higher volume with the same headcount.
Manufacturing — Procurement

Purchase order anomaly detection and flagging

A mid-size manufacturer was processing 1,200–1,800 purchase orders monthly across four divisions. Pricing anomalies — duplicate line items, price deviations, unit-of-measure mismatches — were being caught inconsistently or not at all before approval.

We built a PO review agent that runs each order through a checklist of anomaly patterns defined with the finance team, attaches a structured findings note, and routes flagged orders to the appropriate approver with the specific issue highlighted. The findings note format was designed for their existing approval workflow.

Result: Anomaly detection rate up from an estimated 60% to over 95% on test data. Fewer surprises at audit.

Have a workflow that looks like one of these?

We can talk through whether an agent approach makes sense before you commit to anything.

Get in touch