Third South Solutions · Case studies
What the problem was, what we built, and what changed. Numbers where we have them, and the parts that did not work where we do not.
Field service
A $15M MSP was hand-scheduling on-site visits in a local spreadsheet. The fix wasn't an AI model, but a route solver the operator runs herself.
400+ hrs Given back each year
Insurance
An insurance brokerage relied on a PDF library, OneNote files, and unwritten rules to quote new business. We built a Teams bot that answers team member questions accurately, while citing its sources. The brokerage owns the system and its rule base, with no lock-in to us.
7,000+ rules Extracted from the document library
Portfolio company
A hung process quietly racked up thousands of dollars in AI API charges overnight before anyone noticed. With 18 AI services sharing a handful of API keys, finding the culprit meant hours of log spelunking.
2 hours to 2 minutes Time to find a cost spike
Portfolio company
A small team running a legacy platform was purely reactive: problems surfaced only when a customer emailed angry. Underpayments and stuck jobs went unnoticed for days.
14 checks Running continuously
Portfolio company
A 15-year-old platform run by one irreplaceable engineer was shrinking as customers left for competitors. Outside estimates put a rebuild at $250,000 and 2 to 3 years.
-15% to +50% Change in yearly growth
Portfolio company
A four-person team was stuck waiting on itself: a customer bug meant a support agent filed a ticket, then an engineer had to drop everything to reproduce, diagnose, and fix it, often over days.
Days to 15 minutes Ticket to reviewable fix
Portfolio company
One person was manually scanning six platforms for opportunities, vetting each one, and getting it in front of the right audience.
10 hrs to 10 min Weekly review time