Redesigning How Software Gets Built With AI Agents - Sonar & McKinsey Panel

AI Engineer19m 12s
Prakhar Dixit, Tariq Shaukat and Ali-Reza Adl-Tabatabai beneath Agents at Scale on a black background.
0 comments · 0 votesOpen discussionClose discussion
Sign in to join the discussion

    Prakhar Dixit, Tariq Shaukat and Ali-Reza Adl-Tabatabai discuss why widespread experimentation with AI agents has not consistently translated into scaled business impact. They distinguish isolated coding assistanceAn AI coding agent is a tool-using AI system that can inspect, modify, and validate software within a repository. from redesigning the software development lifecycle, with changes to workflows, tooling and the responsibilities of the people using them.

    Prakhar Dixit, Tariq Shaukat and Ali-Reza Adl-Tabatabai compare metrics for small teams and large engineering organisations, emphasising throughput, quality and developer experience rather than token consumption alone. They explain how implicit organisational knowledgeInstitutional knowledge is the accumulated decisions, practices, context and experience that an organization relies on to work effectively. must become usable contextContext engineering designs how relevant instructions, evidence, state and tool information are assembled for a model's task., and how incremental automation of dependable tasks can build trust in more autonomous agents.

    Original YouTube thumbnailWatch on YouTube

    Video topic coverage

    • Agents & workflows100
    • Coding & tools100
    • Models & learning0
    • Infrastructure & compute0
    • Research & evaluation75
    • Safety & security25
    • Business & productivity100
    • Creative & media0
    • Robotics & perception0
    • Society & policy25

    Share this video

    Prakhar Dixit, Tariq Shaukat and Ali-Reza Adl-Tabatabai beneath Agents at Scale on a black background. With WWW.ARTIFICIAL-INTELLIGENCE.VIDEO, 7 October 2026 and duration 19m 12s.

    Prakhar Dixit, Tariq Shaukat and Ali-Reza Adl-Tabatabai argue that scaling software agents requires workflow redesign, explicit context and outcome-based measurement.