AI and workflow automation case studies

Problem

Policy data arrived as spreadsheets from multiple insurers, each in a different structure, and every client report took hours of manual cleanup.

What we built

Built an automated pipeline that standardizes every insurer's file and feeds a single reporting dashboard.

Result

• Report time cut from 4 to 5 hours to under 5 minutes
• Reporting accuracy up from about 75% to 99%

Problem

Recurring ROC, GST, TDS and tax filings for many clients were tracked in spreadsheets, email and memory, with frequent missed steps.

What we built

Built a compliance tool with recurring task generation, ownership, due-date reminders and real-time client-wise dashboards.

Result

• Status reports in under 15 minutes instead of 4 to 5 hours
• 30+ hours a month saved on coordination

Problem

Clinicians logged sessions in shared spreadsheets, so billing had to fix date formats, durations and missing authorization details before every cycle.

What we built

Built a guided AppSheet portal with validation, auto-calculated durations, approval flows and automatic sync to the billing backend.

Result

• Clinician data entry down from 10 to 15 minutes a day to under 3
• Errors stopped at the source instead of at billing

Problem

Supplier details lived in many Excel files, and every evaluation meant hours of manual research.

What we built

Built a central supplier database with automated research, side-by-side comparison and filterable profiles.

Result

• About 30 hours a month saved on research and reporting
• Reports in under 15 minutes instead of 4 to 5 hours

Problem

Analysts found and filtered suppliers by hand on Google for every client brief.

What we built

Built two automation tools that find candidate suppliers and apply the client's screening rules automatically.

Result

• 85% time saving
• 91% cost saving

Problem

Dispatch typed every delivery address into Google Maps, which only optimizes 25 stops and cannot add time at each stop.

What we built

Built a Python tool that loads addresses automatically, adds buffer time per stop and optimizes the full route through an open-source routing API.

Result

• Manual address entry eliminated
• Delivery-time estimates customers could rely on