Hi all. This week is more of a rant rather than a post. I’ve meet with too many founders recently who have vibe coded something, got stuck, and then reached out to a consultant that provided them with a slide deck of how they sucked and need to hire an engineer, and that cost them over 10k to get that feedback with nothing to show for it except a debt and a sense of failure.
Ok, before I rewrite this whole newsletter again, I’m just going to get into it (oh, i forgot: real john here! lol, people have actually asked for me to write that now. oh an 6 of Spades if you know you know. (got the new spiderman deck from Theory11, and went to Art of Play this week, they were closed unfortunately, but they are opening back on Sept 2 and yes I’ll be there). Ok, here comes a rant…
A founder called me today. He’d gotten further with Claude than he ever expected. Built real product. Real momentum. Then he hit the wall every solo builder hits eventually: three integrations that wouldn’t talk to each other, a nagging fear that he’d left some security hole wide open, and zero idea what to do next. He’d spent the last few days just staring at his screen, convinced he’d finally found the thing AI couldn’t help him with.
We talked for 20 minutes. Twenty. Not twenty hours, not a “discovery phase,” not a statement of work. By the end he knew exactly which integration to tackle first, understood when to build versus when to just buy the boring thing off the shelf, and was fired up to keep going. That’s it. That’s the whole engagement.
Here’s what that phone call reminded me of, and it’s something I’ve been sitting on for a while.
Most consultants are professional diagnosticians who refuse to touch a scalpel
I’ve been in enough rooms with enough consultants to know the pattern cold. They’re smart. Genuinely. They’ve got the pattern recognition, the industry scars, the “I’ve seen this movie before” instinct that actually is valuable. They’ll hand you a roadmap. A threat assessment. A site performance review with a stoplight chart, red yellow green, so you know exactly how bad things are without them having to say it out loud.
And then the meeting ends and they leave.
Congrats, you now have a very expensive PDF that confirms you already suspected you were the problem. Thanks for the diagnosis. Are you going to help me fix it, or do I need to hire someone else for that part too?
McKinsey itself has admitted classic strategy work is now under a fifth of its business, because clients stopped tolerating pure slideware. That’s not a small data point. That’s the market telling an entire industry it needs to start showing up with working code, not just working conclusions.
The gap isn’t knowledge. It’s execution.
This is where AI actually changes the equation, and not in the way most consulting firms want you to think. It’s not that Claude replaces the strategist. It’s that the strategist who also knows how to build no longer has an excuse to hand you a report and vanish.
That founder didn’t need a security audit. He needed someone to sit with him for twenty minutes and say “here’s the one thing to fix first, here’s the thing you can absolutely buy instead of building, and here’s why you’re not actually behind.” That’s not a deliverable you can put in a deck. That’s just doing the work.
I keep coming back to this because I see the same failure mode everywhere right now: companies drowning in AI strategy documents, agent governance frameworks, twelve-step transformation roadmaps, and somehow nobody in the building can tell you which button to click next. The knowledge was never the bottleneck. The willingness to sit in the mud with you was.
I am figuring out that this a real gap in the world right now. You have junior engineers who can’t get a job because of lack of experience or the AI excuse, and you have senior engineers who have moved into director/vp roles who don’t write code any more, but plan, discuss, challenge, doing everything but actually build something.
We have automated, processed, streamlined, stragezied, discussed, collaborated, and every other buzzword variable out there. Except the one that matters: execution.
No one cares what your plan is. They care can you create something that works for them. They don’t want a blueprint, they want working software. I can use AI to generate roadmaps, plans, slide decks, videos, presentations, etc... but even better, I can have it follow those plans and finish.
What does finish look like? What is the definition of done? Simple: You have a working product end to end, ideally with 3-5 clients minimal using your new product.
Hey consultants! You know what done means now. So add that to your line items. You are not just planning, but building the product, creating a marketing campaign, promoting the product, and getting users to sign up for the product you just created.
Stop lying to your clients about how expensive your experience is if you can’t actually deliver something that works. I’ve never liked theories (more often disguised as a hypothesis) because you don’t know until you do the work. You don’t know what works until you show what works.
My mom used to say, “until you have walked the walked”. She walked the walked ALL the time. She worked in tough schools, taught gang members, pregnant teenagers, and so much more. Its hard for a kid to focus if they are dealing with all of that other stuff. She knew what worked with connecting with them, because she knew what didn’t work too.
That is what I do now. I don’t talk theory, I talk about what actually works.
Here’s the thing: this article is about code, but it can be about so much more. You want to build a company culture, you need to do work, not plan it but do it. You want to get your first pull-up, start doing inverted rows everyday. You want to run a mile, walk for 20 minutes and sprint for the last 10 seconds.
I created an AI Country Singer: Rhett Halden, I created social media (instagram,X, YouTube) music, website all of it. Not a plan, but actual music. It is on Spotify and Apple Music, and you can even select his music for your Instagram reels. Not theory, but done! I even a merch shop where you can buy t-shirts and hoodies of his latest EP.
What to actually do about this
If you’re a founder or a builder stuck exactly where that guy was:
Stop paying for another audit until you’ve paid for one hour of someone actually building next to you.
When you hit the “I don’t know if I should build this or buy it” wall, default to buy for anything boring and commoditized, build only for the thing that’s actually your differentiator.
Find someone who will get their hands dirty in your actual codebase, not just your architecture diagram.
And if you’re the consultant reading this feeling a little called out, good. That’s the point. The report isn’t the value. The next line of code is.
That founder is unblocked and shipping again. The security fear was well founded, but he knows where to go for that. Fixed in ten minutes once we actually talked about it together instead of writing a paragraph about it. That’s the whole business model that’s about to eat a huge chunk of consulting: less “here’s what’s wrong with you,” more “let’s fix it right now, together.”
Go build something amazing. Or better yet, go help someone else finish building theirs.
John Mann is the founder of Startups and Code LLC, a software engineering executive, and the guy who built Cash Critters for $50/month because constraints are a feature, not a bug. Subscribe for weekly takes on AI, startups, and building things that matter.