Airhelp is a service that helps airline passengers in 30 countries file claims (for delays, lost bags, overbookings, and cancellations) structured to increase the likelihood of paying out; the bots have made $930m in successful claims to date, and the company behind it only collects a commission when a claim succeeds. The service uses internal machine-learning systems that sifts through claims to identify high-potential claims, as well as correctable defects in claims, like missing documents. The system is similar to the many DoNotPay bots (previously), including one that helps passengers claim compensation if there is a price-drop after they buy their tickets.

AgA (short for Agent’s Assistant) and Docky will help the company with customer service and automatic assessment of claims. AirHelp says it has been testing these bots internally since last year and that they have already assessed 30 percent of claims it receives with 95 percent accuracy. After making an assessment, if AgA comes to the conclusion that its decision is not perfect, it informs the operations agents to focus on the tasks needed to complete the assessment. Docky acts as an assistant operating within AgA to request missing documents from customers and handles 40 percent of those assignments.

AirHelp’s new bots collect airline compensation for passengers [Manish Singh/Venturebeat] (via /.)