An AI assistant that runs the issue desk for a 230,000-customer migration

Vandebron, a Dutch energy supplier, is moving around 230,000 customers onto a new platform in groups. Every group that goes live creates a stream of issues that two companies need to sort, route and fix quickly.

• Issues were raised in a shared chat channel. They only became tickets if someone remembered.
• Working out what an issue was about meant reading threads 30 to 50 messages long.
• Issues on Vandebron's side weren't tracked anywhere.

• Built an agent that turns every reported issue into a fully filled-in ticket within 15 minutes, with no duplicates.
• It tags the right owner on both sides, writes a summary of the whole discussion, and posts updates back to the original thread so the person who raised it always knows where it stands.
• Every hour it re-reads every open ticket and marks it as one of ten states, such as waiting on someone, fix due, or workaround in place, quoting the messages it based that on.
• Split the work into plain code for predictable steps and AI only for judgement, and added a free check so the AI only starts when there's something new. That cut the monthly running cost from about £490 to £39.
• Designed it to catch up on its own after outages (tested on a 45-minute and a 15-hour gap) and to never drop a ticket to save money.
• Moved it onto company infrastructure with a dashboard the whole team uses, and wrote up the lessons so the next agent starts from them.