Vaibhav Gupta on Building Software at Agent Speed

AI Engineer21m 32s
Vaibhav Gupta in a blue top beside the blue and white headline Build at Agent Speed? on black.
0 comments · 0 votesOpen discussionClose discussion
Sign in to join the discussion

    Vaibhav Gupta opens with a deliberately provocative account of a team that does not conduct routine code reviews, lets engineers use different AI tools and works in parallel. Rather than endorsing unchecked generated code, he describes replacing some manual coordination with a short, model-agnostic architecture documentContext engineering designs how relevant instructions, evidence, state and tool information are assembled for a model's task., versioned design documents, required human readers and automated checks on dependency boundariesDeterministic software verification checks an output with a repeatable procedure that produces the same result for the same inputs and state.. These are the practices he says his team uses while building a programming language.

    Vaibhav Gupta then outlines an agent-driven feedback loopAn AI feedback loop occurs when AI outputs or their consequences become inputs that influence later model or agent behavior.: agents generate programs, inspect tool-use transcripts and surface possible language or developer-experience problems; humans decide which findings are real; agents can propose fixes; and alternatives can be compared by tool calls, errors and outcomes. He argues that execution tracesAn execution trace records the sequence of operations and results produced while a system carries out a task. and navigable views of code can help engineers understand a system without reading every line. His assertions about team productivity, stable architecture and tracing costs are first-person claims, not independently verified results.

    The second half shifts from process to agent-first language and tooling design. Vaibhav Gupta demonstrates ideas for semantic code navigation, runnable functions, portable command-line tools, inferred error types and calls across language boundaries. He argues that compilers and type systemsA type system assigns and checks categories of values and expressions to constrain which operations a program may perform. can enforce useful guarantees for both people and agents while allowing adoption from existing languages rather than requiring a complete rewrite. The talk ends by urging engineering teams to adapt their processes to agent-speed development, while leaving open how broadly the demonstrated approach generalizes.

    Original YouTube thumbnailWatch on YouTube

    Video topic coverage

    • Agents & workflows100
    • Coding & tools100
    • Models & learning0
    • Infrastructure & compute0
    • Research & evaluation45
    • Safety & security0
    • Business & productivity55
    • Creative & media0
    • Robotics & perception0
    • Society & policy0

    Share this video

    Vaibhav Gupta in a blue top beside the blue and white headline Build at Agent Speed? on black. With WWW.ARTIFICIAL-INTELLIGENCE.VIDEO, 31 July 2026 and duration 21m 32s.

    Vaibhav Gupta argues that teams using AI coding agents need stronger system-level safeguards even if they reduce line-by-line code review. He describes design-doc review, architecture checks, agent-driven testing and language features intended to make code easier to inspect and trust.