Case Studies

What we built, and what it actually achieved

Every number below is measured against a real baseline and scored on the client's own historical data. Where a system fell short, we say so — including what we changed as a result.

Manufacturing — made-to-order fine jewelry

AI-powered vision-enabled agentic solution for ERP order intake automation

Custom orders arrived as free-text email with sketches and photos attached. Staff spent 15–30 minutes keying each complex order into Business Central. We built an intake agent that reads the thread and its images, fills ~25 job-card fields with calibrated confidence, and stops at a human approval gate.

83%

Field-extraction accuracy across 11 real orders

97.7%

Exact match on the eight critical job-card fields

Hallucinated fields

79 sec

Mean time to a reviewable draft order

Read the case study

Have a process that runs on email and hand-keying?

The pattern generalises: an unstructured request arrives from someone who knows their trade but not your field names, and a person turns it into a structured record by hand.