AI & software projects

Problem

An insurance claims platform received accident notification reports, odometer photos and vehicle ID plates as unstructured images attached to each claim. Staff retyped the same fields — odometer reading, VIN, accident narrative — by hand from every attachment before a claim could be triaged.

Approach

Built an event-driven pipeline that classifies each attachment, then routes it to the right extraction model: fast plate recognition for number plates, layout-aware OCR for odometer readings and VIN plates, running on serverless infrastructure that scales to zero between claims.

Outcome

Key-information extraction pulled VIN, odometer and ANR straight from photos.

Problem

Customers of an insurance claims platform had to call or log in just to ask "where's my claim", tying up staff time on questions the claim record could already answer.

Approach

Built a conversational assistant with dual-mode authentication and a web front end, deployed as coordinated services behind a gateway so it can answer plain-language status questions without a phone call or a login.

Outcome

Verified across four user roles and eleven real claims in structured acceptance testing, giving customers a plain-language status answer on demand instead of a support queue.

Problem

Automotive repair quotes arrived as unstructured PDFs, and every labour line, part and total had to be re-keyed by hand before a claim could be compared or approved.

Approach

Built a document-AI pipeline that runs text detection ahead of a layout-aware model fine-tuned on real repair quotes, converting each PDF into a structured record of labour items, parts and totals through a set of coordinated services.

Outcome

Reached an 88.79% F1 score across 189 extracted entity types on 200+ real-world repair quotes, replacing manual re-keying with structured data.