I’m going to be grumpy today and complain about something trivial: I’m frustrated by how much AI is touted as the ultimate multiplier to any business without explaining what it actually takes to get good results. It takes hard work, work that has been established as good practice and followed by the top software shops for decades. And yet from what I gather, this is exactly the kind of work most eager AI buyers have been avoiding since well before generative AI was a thing.
Agreed. An agent only multiplies what’s already in the codebase. If you’ve got tests, clear boundaries and the rules written down, it genuinely flies. If it’s the usual undocumented mess, you just get more mess, faster. Which is probably why the shops that dodged that groundwork for years are getting the least out of AI now. There’s nothing solid under it to build on.