Harness Engineering: How to Build a Software Factory - Dru Knox, Tessl

AI Engineer20m 31s
0 comments · 0 votesOpen discussionClose discussion
Sign in to join the discussion

    Video summary

    Dru Knox defines a software factory as a system in which agents produce the shipped product while engineers improve the machinery around them. He separates autonomy, the amount of corrective intervention required, from automation, the amount of work teams trust to run without manual review, and treats product quality as a distinct measure.

    Dru Knox describes three feedback loops. Cheap inner-loop checks help coding agents correct work before a pull request; more expensive outer-loop checks support review after submission; a meta loop studies failures, corrections and user feedback to improve the earlier checks. This is a proposed engineering approach, not evidence that every team can remove human oversight.

    Dru Knox argues that improvement requires a legible control plane, usable execution environments and governed access to the tools and services agents need. Shared issues, pull requests and playbooks make mistakes available for analysis, but infrastructure setup, rapidly changing practices and unplanned improvement work remain practical obstacles.

    Original YouTube thumbnailWatch on YouTube

    Share this page

    Dru Knox against a black background beside the blue-and-white headline “BUILD A SOFTWARE FACTORY”. Framed in blue with WWW.ARTIFICIAL-INTELLIGENCE.VIDEO, 6 October 2026 and duration 20m 31s.

    Dru Knox describes how visible workflows, practical agent access and three feedback loops can improve coding-agent autonomy without sacrificing product quality.