Board-worthy problems. Brag-worthy results.
The cause was rarely where it seemed. The solution was always more than a fix. Case studies from Phillip Hunter’s 30+ years of AI, voice and enterprise product work.
Safe, effective AI-powered assistance for 39 million US residents
Led the behavioral testing behind California’s new AI assistant, AskCA, as lead volunteer consultant: 129 simulated-resident conversations, ordinary and adversarial, with every answer scored against AskCA’s own instructions and the 5 high-stakes checks scored by judges from 3 AI model families. Quoted in the Governor’s launch.
How we tested it: Build trust in, test trust out ↗Architecting a much loved retailer’s high-volume voice commerce agent
A voice commerce agent for loyal, particular callers: flexible, natural conversations, scoped, prototyped and tested before callers meet it.
Built a quoting engine to speed up a specialty insurance agency
Coverage checked, priced from the agency’s own rates, application filled and queued for a person to approve. AI working for an everyday business.
A launch the client was ready to pull, exceeding its goal in 60 days
The real problem wasn’t the AI. A choke point upstream kept calls from reaching the paths that resolve them.
Teaching an AI voice system to learn while it worked
Routing accuracy target with almost no training data; routing time cut from 30 seconds to under 10. Practice carried through the company’s acquisition.
The no-code bet that reignited growth
Putting skill creation in consumers’ hands drove a 2000% increase in active skills.
When the OG cloud couldn’t update a screen
A design system and 30+ redesigns turned a fragmented console into one developer experience.
An answer in the content haystack
Turning a huge expert library into on-demand, multi-source answers in the flow of work.
Speechicon · Cole Insurance · US Digital Response · O’Reilly · Alexa · AWS · Collibra · Kasisto · [24]7.ai · Intervoice · Pulse Labs · Charter · E*Trade · Southern Power · Cigna · First American