Daily Kickoff

Up to seven things a day for people building with AI. Fewer when there aren't seven.

  1. AI Code Review at Scale: LinkedIn's Multi-Agent Approach

    At LinkedIn's scale, relying solely on human reviewers or simply putting an off-the-shelf AI reviewer in front of GitHub is not an effective way to manage PRs.

    InfoQ AI/ML

    #
  2. Spline rebuilt its entire 3D editor. Then it handed the keys to Claude Code.

    Spline released V2, a rebuild of its 3D editor whose new MCP Server lets Claude Code, Cursor, Codex, Google Antigravity and VS Code work directly on live, editable scenes. The server ships bundled with the macOS and Windows desktop app, binds to 127.0.0.1, and is protected by an origin allowlist.

    The New Stack agentic coding

    #
  3. Citizens Build, Agents Execute, Experts Govern

    TL;DR Why building an app over the weekend isn't the same as building enterprise software I’ve noticed an interesting gap opening up over the last six months. It isn’t really a gap in technology. It’s a gap in what different people think software engineering actually is.

    Martin Fowler

    #
  4. How Code in the Age of Artificial Intelligence Becomes Write-Only and Disposable

    At QCon London, Phillip Mortimer argued that AI-generated code becomes "write-only" — too dense to read, with tests serving as the documentation — and disposable, since rewriting is often easier than debugging it. He proposed automating code review and having AI agents monitor observability data to raise pull requests for the most common problems, freeing developers to focus on creativity.

    InfoQ Culture & Methods agentic coding

    #
  5. AI is showing a revenue payoff: Carnegie Mellon

    Despite positive signs on the revenue front, AI adoption has yet to translate into significant operating-margin gains, the study found.

    CIO Dive

    #