All projects
AI & Automation Coastline Restorations 2025

From faxed invoices to a queue you can trust.

A restoration contractor was re-typing supplier invoices into claim files by hand. We built an extraction pipeline that reads the documents, proposes the line items, and asks a human only when it is unsure.

Client
Coastline Restorations
Industry
Insurance restoration
Location
Calgary, Alberta
Timeline
12 weeks
Team
2 engineers, 1 designer
app.coastline.ca/intake18 in queue

Intake queue

PDF
Claim_88421.pdfWater damage · Edmonton
Extracted
PDF
Invoice_2209.pdfAllied Plumbing · 3 pages
Review
PDF
Photos_18.zipSite 4 · 12 images
Linked

Extracted fields

94% confidence
Claim numberCLM-8842199%
InsuredM. Tremblay97%
Loss typeWater damage94%
Estimate total$14,860.0091%
Deductible$1,000.0088%
Outcome
92% Line items auto-extracted Without human correction
4.1h Saved per claim Across a 38-claim sample
0 Duplicate payouts Since go-live in March
The challenge

Claim Intake & Line-Item Extraction

Every claim arrived as a folder of PDFs: supplier invoices, adjuster notes, photos, and a hand-typed estimate. A coordinator rebuilt the line items by hand before the file could move.

Volume doubled in storm season, and the errors that crept in during the rush were expensive to unwind after the fact.

Stack
  • Python
  • OpenAI
  • PostgreSQL
  • S3
How we did it

Four decisions that made it work.

  1. 01

    Read the worst documents first

    We tuned against 600 real invoices — including scans, faxes and three suppliers who still use dot-matrix.

  2. 02

    Never guess silently

    Below a confidence threshold, the field is left blank and highlighted for review rather than filled with a plausible number.

  3. 03

    One screen for review

    The coordinator sees the document and the extracted fields side by side, with a single keystroke to accept the page.

  4. 04

    Learn from corrections

    Every correction is logged with its supplier and document type, and feeds the next monthly tuning pass.

“It does the boring part perfectly and it tells us when it is unsure. That is the whole reason the team trusts it.”

Marc Delacroix Claims Manager, Coastline Restorations
Take the First Step

Tell us where the work slows down.

Tell us what is slowing your team down. We’ll analyze your process and outline a practical architecture.