The state of AI in 2026: On the road to ROI

(mckinsey.com)

21 points | by swolpers 1 hour ago

7 comments

  • ivolimmen 53 minutes ago
    > Organizations are using agentic coding tools to build software in-house in lieu of purchasing it. Nearly a third of respondents (32 percent) report that their organizations have decided against buying one or more software products or features because they could be built internally with agentic coding tools.

    People think they can do it themself... kind of like how everyone build their own database using Microsoft Access in the 90's. When all software developers needed to repair all the issues...

    • PaulRobinson 37 minutes ago
      I am at a point in my career where I'm figuring out where I want to spend the last 15 years of it. I don't want to work in corporate for a long stretch of it. It seems to me, being a consultant to fix all those messes could be a good seam of code face to get stuck into...
      • rwmj 31 minutes ago
        It's going to be a horrible job though, the equivalent of fixing Y2K bugs in Cobol code except with code bases that even more vast and unintelligible.
        • sph 3 minutes ago
          Yeah, unreasonable deadlines (these are the norm) spent trying to untangle a mass of overly verbose spaghetti code, and chances are there is no budget for you to do it properly, they contracted you only for a ‘bugfix’. It’s just more technical debt on top of technical debt.

          No, thank you. I’ll leave the underpaid disinfestation job to someone else.

        • jeffreyrogers 17 minutes ago
          The LLMs are pretty good at helping with that though.
          • sph 1 minute ago
            [delayed]
        • karmakurtisaani 13 minutes ago
          It will be messes of python scripts running on some ancient version of python that you have to switch between scripts. All in a folder on some laptop with an outdated OS that you cannot update or everything will break. Business logic obviously not documented anywhere, just mountains and mountains of slop readmes that might be accurate, but also might not be.
    • codingdave 8 minutes ago
      Except that isn't how it played out. Most of the Access DBs, spreadsheets, and even SharePoint, Notes, and early Salesforce apps worked just fine without any help from devs. Yes, the devs got called in when those solutions needed to scale beyond a single department, but most of them never did.

      It is far more plausible that we'll see that pattern again - small, department-level vibe coded apps will be around. And things that need to scale bigger will need professionals.

  • mjhay 58 minutes ago
    The ROÍ will be happening any day now, we promise. Please hire more McKinsey consultants who say they’re AI experts.
    • walt_grata 53 minutes ago
      Is there a company that has been more damaging to the software industry than these jokers?
      • dgellow 38 minutes ago
        Oracle maybe?
      • inigyou 51 minutes ago
        Apple?
        • piva00 46 minutes ago
          The one who invested in LLVM?
          • inigyou 27 minutes ago
            The one who normalised needing approval from the device maker to run code.
        • MeetingsBrowser 25 minutes ago
          How so?
        • sublinear 43 minutes ago
          I'm about as much of an Apple hater as anyone else, but you're probably thinking of user interface design (or CUPS).
  • zerolayers 15 minutes ago
  • kittikitti 1 minute ago
    I wouldn't trust anything McKinsey publishes.
  • dgellow 35 minutes ago
    Do I understand correctly that means there is no AI ROI to show off yet? If correct that’s pretty bad, no?
  • lukewarm707 41 minutes ago
    i look forward to mckinsey being replaced by ai.
    • antisthenes 13 minutes ago
      No need, you can replace them with a single sentence.

      Do the most unethical profit-maximizing thing, but also account for the eventual lawsuits and loss of goodwill in your calculation.

  • simianwords 21 minutes ago
    As expected the thread is filled with smug comments on how it is definitely not ROI positive.

    The thing I think about is AI is already at that spot where you don’t need a survey or a Randomised Controlled Trial to prove it makes one productive. Sometimes things are that obvious. But these kind of tests and surveys appeal to a certain kind of person who considers IMO the wrong type of things as rigorous.

    • jeffreyrogers 12 minutes ago
      It makes organizations more productive at producing code and doing other tasks, but translating that into something that affects PnL is different. Where I work it's sped up individual tasks I've worked on but I don't think it's sped up delivery timelines of any of the major projects I'm involved in. We just added additional verification work with the extra cycles the engineers have now. It's not like that work is useless. It will probably mean I have less debugging to do in the future, but when you look at how the business makes money I don't see it making a big impact.
      • simianwords 9 minutes ago
        Based on what you said, would you think firms would dial down AI use in the coming years? If not it stands to reason that it did have big impact.