We Built an AI Support Agent That Resolves 80% of Tickets - AssemblyAI

AI Engineer16m 19s
Matt Lawler beside the headline AI Support Agent
0 comments · 0 votesOpen discussionClose discussion
Sign in to join the discussion

    Matt Lawler describes the support workload created by AssemblyAI’s reported volume of new API signups and why an earlier third-party support bot did not meet the team’s needs.

    He explains how its agent Joey combines a local documentation copy, embedding retrieval and filesystem searchRetrieval is the process of selecting relevant stored information and returning it to an AI system for the current task., with rapid deployment and updates. He reports that it resolved 80% of inbound tickets end to endWorkflow automation uses software or AI to complete a connected sequence of routine steps with less manual effort. during its first week, while escalating other cases.

    Lawler demonstrates a voice interfaceA voice interface lets people interact with software through spoken input and audible responses. using the company’s API and discusses the value of building with the same tools as customers. The performance and cost figures are the presenter’s account, not independently verified.

    Original YouTube thumbnailWatch on YouTube

    Video topic coverage

    • Agents & workflows100
    • Coding & tools50
    • Models & learning25
    • Infrastructure & compute50
    • Research & evaluation25
    • Safety & security0
    • Business & productivity100
    • Creative & media0
    • Robotics & perception0
    • Society & policy0

    Share this video

    Matt Lawler beside the headline AI Support Agent With WWW.ARTIFICIAL-INTELLIGENCE.VIDEO, 4 October 2026 and duration 16m 19s.

    Matt Lawler describes AssemblyAI’s support agent and the team’s reported results and architecture.