Every services firm runs on the same hidden equation, whether or not anyone has written it down: revenue is a function of headcount. To grow, you hire. To take on more work, you staff up. To protect margin, you push utilization. The whole apparatus of an agency, a consultancy, or a professional-services firm is a machine for converting human time into invoices, and the better you run it, the more cleanly that conversion happens.

We talk to a lot of leaders who have already made up their minds. AI is a fad. AI is garbage. They tried it, it underwhelmed, and they filed it next to every other overpromised technology a vendor once swore would change their business. It is a reasonable conclusion, and most of the time it is an honest report of a real experience.

It is also, almost always, a report on the wrong experiment.

There is a quiet assumption buried in most enterprise AI adoption: that the path to better output is a better single prompt. Refine the wording, add more context, raise the stakes in the instruction, and the model will eventually produce the answer you wanted. That assumption is responsible for a lot of plateaued AI programs. It treats a probabilistic system as if it had one best answer waiting to be unlocked by the right key.

Twenty years ago, email had an identity problem. Anyone could send a message claiming to be from your domain, and the receiving server had no reliable way to tell a real [email protected] from a spoofed one. Phishing thrived in that gap. The fix wasn't a smarter spam filter — it was an authentication layer. Domain owners got a way to publish a policy about who could send mail as them, prove that legitimate senders were legitimate, and get reports when someone tried to abuse their identity.