San Francisco-based Lorikeet, an artificial intelligence support platform for regulated industries, today announced the general availability of Coach, a self-service analytics agent that evaluates support tickets to help organizations diagnose AI problems.
The company said Coach tackles critical issues with AI support where visibility becomes an issue at scale, including understanding why numbers are spiking, how customer sentiment is moving in a particular direction, and which specific topics, policies or configurations are causing problems.
Customer satisfaction surveys and scoring, called CSAT, may provide a tapestry to understand the environment, but employees must read and aggregate them manually and diagnose the cause. Lorikeet wants to soar above that and give enterprise users a bird’s-eye view.
“You’ve deployed AI support, but you’re flying blind,” said Chief Executive Steve Hund. “CSAT tells you if customers are happy, but not whether the AI is doing what you told it to do.”
According to Hunt, the power behind Coach is that it’s a diagnostic system that explains exactly which conversations and topics are failing and why, rather than that they failed. This provides the trajectory needed to make actual change.
Lorikeet said Coach operates on two core capabilities in parallel: thematic analysis and ticket quality score.
Thematic Analysis uses AI clustering to categorize tickets into substantive topic buckets, then breaks them down and uses that information to provide performance metrics. The company said this reveals what aggregated metrics can hide; the same AI can achieve 91% successful resolution on one topic but only hit 56% on another.
Ticket Quality Score looks at every conversation and compares it against a scorecard, using quality checks to flag issues on a traffic-light scale. It uses a customizable set of definitions based on organizational standards, whether that’s reinforcing the app as the source of truth, avoiding certain refund scenarios, or ensuring the AI doesn’t expose internal terminology.
The company said this allows teams to move away from traditional quality assurance tools that sample a small percentage of human agent tickets, or native analytics, and instead view a holistic portion of the emergent majority of support interactions.
“The existing QA category was built for a world where humans answered every ticket and you could afford to sample,” said Hind. “But when AI is handling thousands of conversations a day, you need 100% coverage.”
In an interesting twist, Lorikeet added that Coach can handle both AI and human-handled tickets, enabling teams to maintain consistent quality standards across both domains.
The company said Coach is available to all customers and is now offered as a standalone product.
Image: News/Microsoft Designer
Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.
- 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more
- 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network.
About News Media
Founded by tech visionaries John Furrier and Dave Vellante, News Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.
