Last night I did something I haven’t done in 30 years of writing software: I handed a piece of code the keys to a real decision and walked away.

Not “run this script.” Not “generate this function.” I wrote down a mission, a budget, and a set of rules, gave an AI agent standing authorization to act on them without asking me first, and told it to check in daily. Then I went and did other things.

This week’s special-edition newsletter is a two-parter, because the story only makes sense in order. First, the skill library that makes this repeatable instead of a one-off trick. Second, what happens when you actually point it at a real business problem and let it run.

Subscribe now

Part 1: Agent Skills — packaging judgment, not just prompts

Anyone who’s tried to get consistent, good work out of an AI coding agent knows the problem isn’t capability. Modern models can write the code. The problem is context — the fifty small decisions a competent engineer makes without thinking about it, that a fresh agent has no idea it’s supposed to make.

Do you branch before touching main? Do you verify the diff before merging? Do you actually run the tests, or just claim you did? Do you check that main is still clean before you push? A capable model with none of that context will happily skip every one of those steps and tell you it’s done.

So I started building Agent Skills — a public repo of portable, reusable skill packages built on the emerging Agent Skills format, authored with Codex as the primary runtime. Each one is a folder: a SKILL.md describing the workflow, reference docs for acceptance criteria and output templates, and an agent-specific config. Drop the folder into .agents/skills/ in any repo, and the agent picks it up.

What’s in there right now:

• inspect-and-finish-pr — review a pull request, resolve the actionable feedback, verify it, leave the merge decision to you

• build-from-product-idea — shape a rough idea into scope with you, then implement the approved plan and open a verified PR

• debug-with-evidence — diagnose from logs and repro steps and propose a fix before touching code

• review-ui-against-requirements — check a flow against written requirements and report gaps before changing anything

• daily-briefing, deploy-and-verify, prepare-for-interview, find-the-missing-question

That last one is my favorite, and it’s the whole philosophy in one skill: before you build the thing, it forces the agent to find the assumption nobody’s tested. “We want to build a chatbot because five users asked for one” isn’t a spec, it’s a guess wearing a spec’s clothes. A good skill’s job is to catch that before code gets written, not after.

The unlock isn’t that the agent can write code. It’s that I can write down how I want work done exactly once, put it in a skill, and every future task inherits that judgment instead of me re-explaining it in every prompt.

Part 2: Astra Lab — what happens when you actually let go

Here’s where it gets uncomfortable, in a good way.

I started Astra Lab as a real test: not “can an agent write code,” but “can an agent run something.” I wrote an AGENTS.md with a mission — find a real recurring problem, build something useful, pursue revenue — and standing authorization to research, build, test, commit, and push without a new prompt each time. Then I put a fence around it: strictly under $200/month in new spend, no paid services or API billing enabled until there’s a real provider-enforced hard cap, no customer outreach without an explicit go-ahead, and no claiming results that aren’t backed by evidence.

It runs on a schedule — twice a day, 45 minutes a session, one overlap lock, a PAUSE file if I need to kill it — using Codex CLI through my existing subscription. It reads its own status file, decides the next useful task, does it, runs the tests, updates the record, and pushes. I read the diffs. I don’t write them.

In its first day, it shipped Migration Receipt: a browser-only tool that compares a source and destination CSV export from a CRM migration and shows you what’s missing, what’s extra, what changed, and what’s ambiguous — no uploads, no storage, nothing written back to anyone’s CRM. It’s a bet, not a business: the current evidence shows the migration-tooling space already has real competitors, and the agent said so in its own status report instead of dressing it up. It bought the domain ($10.88, receipts included), wired up Cloudflare DNS, deployed to Vercel, added a real 404 page, a sitemap, mobile checks, and a Startups and Code attribution footer — because I told it that credit was non-negotiable, and it never dropped it once.

It’s not public yet. I’ve got a Product Hunt launch scheduled for Tuesday, September 15th, and you can already poke at it early: astralab.work.

The honest part, the part I want you to sit with: the most valuable thing the agent did wasn’t the code. It was refusing to fake progress. Its own status file says, in plain language, that the demand for this specific tool is unvalidated and it might get killed after more discovery. I didn’t write that sentence. It did, because I told it evidence beats optimism, and it took me at my word.

What you can actually do with this

You don’t need my exact setup to get the point:

1. Write down the judgment, not just the task. Next time you catch yourself re-explaining “and don’t forget to run tests” to an agent, that’s a skill waiting to be extracted. Package it once.

2. Give it a fence before you give it freedom. A budget, a kill switch, and a rule against claiming unverified results will do more for your trust in autonomous work than any amount of prompt engineering.

3. Make it report honestly, on purpose. Tell your agent explicitly that “no evidence yet” is an acceptable answer. Most of the bad autonomous-agent stories I hear are really stories about nobody giving the agent permission to say “I don’t know.”

I’ll keep you posted on whether Migration Receipt finds a real buyer or gets retired. Either outcome is useful. That’s the point of running it as a lab instead of pitching it as a launch.

I’m planning to have a new tool every week (based on budget of course). But let’s see how far it goes without me.

Go build something amazing. Or better — go build something that’s allowed to tell you when it isn’t working.

Share

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.

Subscribe

Gartner dropped a number this month that should have been a headline everywhere and instead got buried under another round of AGI press releases: more than 40% of agentic AI projects will fail by 2027. Not "underperform." Not "need iteration." Fail.

I read that and laughed, then got annoyed, then laughed again. Because I've watched this exact failure rate before, wearing a different costume. Digital transformation. Agile transformation. Cloud migration. Big Data (remember when that was capitalized like a proper noun?). Every single one of these had its own version of the 40% club, and every single postmortem said some version of "the technology wasn't ready." The technology was fine. The technology is always fine. What wasn't ready was the org chart pretending a rebrand counts as a strategy.

Nobody's Agent Failed. Their Plan Did.

Here's what actually happens inside that 40%. Somebody in a leadership meeting says "we need an AI agent strategy" the way people used to say "we need a digital strategy," which is to say: as a vibe, not a plan. Nobody defines what the agent is actually supposed to own. Nobody decides what happens when it's wrong. Nobody builds the review loop before the agent starts making decisions that matter. Then six months later there's a slide deck explaining why "the AI didn't deliver ROI," and the AI gets blamed for a scoping failure that would have killed a junior developer's first project too.

I built Cash Critters for about fifty bucks a month. One person, no committee, no six-week alignment offsite to agree on what "done" means. I knew exactly what it needed to do because I decided that before I opened a single tool. That's not a humblebrag, it's the entire point. The tools didn't get easier because I'm special. They got easier because I removed every layer of organizational theater that usually sits between an idea and a shipped thing. Enterprises don't have that luxury by default, they have to build it on purpose, and most of them skip that part because it's less fun than announcing a strategy.

The uncomfortable truth in the Gartner number is that agentic AI didn't introduce a new failure mode. It just moved faster into an old one. When you used to plan poorly, you found out you were wrong in eighteen months, after a launch that quietly underwhelmed everyone. Now an under-scoped agent finds out it's wrong in eighteen minutes, at production scale, in front of a customer. The technology got faster. The discipline didn't catch up. That gap is the entire 40%.

What Actually Separates the 60% From the 40%

The teams that aren't going to be in that failure statistic aren't smarter and they don't have better models. They just did the boring work first.

• They picked one narrow, verifiable task for the agent, not "customer support" as a category but "resolve refund requests under $50."

• They decided upfront what a wrong answer costs, and built the review step before the agent shipped anything to a real user.

• They measured something specific within weeks, not a quarter, so they knew fast whether they were in the 40% or the 60%.

• They treated the agent like a new hire with no institutional judgment yet, because that's exactly what it is.

None of that requires a frontier model. It requires someone in the room willing to say "what does this actually need to do" before anyone says "what should we call this initiative."

Go Build the Boring Part First

I get why nobody wants to hear this. "Scope your agent narrowly and build a review loop" doesn't fit on a keynote slide next to "we've entered the agentic era." But the org that skips the boring part is the org that ends up as a Gartner statistic, and the org that does the boring part is the one that gets to keep building while everyone else is writing a postmortem about a technology that was never actually the problem.

Pick the smallest real task you can hand an agent this week. Define what wrong looks like before you find out the hard way. Ship it, watch it, and let the data tell you if you're in the 40% or not. That's the whole strategy. It always was.

Go build something amazing.

Share

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.

Because basically that is all people could do today. OpenAI, Claude, and Grok all went down at the same time. Shout out to Gemini for keeping the lights on for vibe coders.

However, here’s what happened in real life. People went to social media to complain. Everyone asked what AI tool is still working. How can they finish their job today?

Here’s what I did: Check the status of the one’s I use. Realize they were down, reviewed my tasks for today, and get this: I started coding. Well, I actually started debugging to see what the issue actually was that I was working on, but I opened VS Code, kicked off a docker container, synced some data, updated environment variables to test on different environments, reproed the issue, and then… I fixed it. Not me and Claude, not Codex, not AI. ME.

How is that even possible in today’s AI crazy world?

Because I know how to code. More importantly I know how to debug. I also know how to trace code. I know pitfalls that happen usually when something happens that is “unexpected”. How can I know all of that without an AI telling me what is wrong? Because I’ve been doing it since I was 9 years old.

I LOVE coding. Coding with AI is a lot faster, but I still like to know what the hell that AI is doing in some cases. Don’t get me wrong, in other cases, I don’t care, did it solve the problem, fix the text change, change the color, update the CSS, great. Did it make a security architecture decision that would violate SLAs, compliance laws, and performance, ok, then I care… I care a lot.

I’ve been invited to so many meetups, conferences, and groups to talk about how to implement AI. It is the tech version of talking about Taylor Swift’s wedding. Everyone is talking about it, but no one talking about it actually attended it. And in this case, they didn’t implement it ever.

They all have hypothesis on what works. How to protect your data. How to make your engineering team more efficient. They are all selling you courses, consultancy contracts, and none of them have actually done it. I have. I have built AI personas, AI agents, taught numerous people about setting up AI locally, how to handle easy tasks, and complex tasks. I’ve done full youtube videos of how I created a persona from scratch to a new YouTuber.

Those people selling you that garbage, the Don Lapre of AI, (if you know who he is, you were a child of 90s). Ask them this: “What did you try that didn’t work, and where would you specifically recommend not using AI in an engineering organization?”

Most people will who haven’t done it, will respond: Our framework actually handles those cases, and even allows the flexibility to adhere to your custom business rules. That is fluff and them redirecting the question. They haven’t done it, they want you to pay for something from someone who doesn’t have the pain of actually doing it.

The thing I’m learning more and more is that content is simply that content. It may not be useful, practical, or even entertaining. But there is a lot of it.

Ok, I’m going to go on tangent right now, because this is not my regular weekly newsletter, that will be coming out this weekend, but for those subscribing, this is a random post about things…

I’ve been following the Lindsay Clancy case for 6 weeks now, and the jury is on day 6 I think of deliberating that is over 30 hours of discussing the case. If you don’t know, quick summary: She allegedly strangled her three children due to Post-Partum Psychosis. That is the defense. Anyway, I won’t get into the details of the case, because that’s not what I want to get into. I want to talk about content. The jury is deliberating for 6 days. That is 6 days of news channels speculating about what they are doing, what are the outcomes, how can they view it this way or that way, what if… Anyway, my point is, it is filler. They should say, we are going to go off the air until the jury comes back with a ruling, put up a Jury Watch clock, and go home until the jury comes back. It is not real content. It is like all the annoying teaser, click bait insanity: 10 ways to lose 10 pounds by October. The best 8 places to live in NY. The secret underbelly of Big Tech and how you can protect yourself. IT’S ALL GARBAGE to get your attention. And the algorithms are GOOD, I mean REAL good. So good, they are getting sued for destroying teenagers.

Anyway, I’ve learned so much about the YouTube algorithm recently because I have created 3 channels of people and their content is getting over 1k views on almost every post. It’s crazy. They aren’t even real people, but newer content gets raised up, and now you have to keep on the wheel to deliver content to keep those numbers up. You can look at my Startups and Code channel and I have about 16 views. Why? Because the content is 2 years old and I haven’t posted regularly.

Anyway, my point in this post is simple:

AI is a tool, use it carefully. Know how to operate without it if needed. Generate content all you want, but know why you are doing it. For fun, for entertainment, for education, who cares, but have a real intent behind it.

Also, never get so engrossed in it that you forget how to say hello, hold the door for someone, and smile at a stranger to make them have a little brighter day.

That’s all. I’m going to generate some YouTube short now for Eliza and Nova. Rhett is doing fine right now. LOL Let’s see if this post tracks as 100% human generated, because the lack of consistency, randomness, and crazy rants, no way an AI could do it. No picture this time other than the outage too. So let’s see what it says.

See you this weekend on the regularly scheduled newsletter. Thanks for your support and encouragement to keep me doing this. I truly do appreciate it.

Subscribe now

A few weeks ago, I pulled up a dashboard I’d built to feel good about myself.

It was tracking AI assisted output across a few projects I’m close to. Pull request open commits merged into feature branches, lines of code touch per week. Every number was up and to the right. I remember sitting there thinking, This is it. This is the velocity everyone’s been promising. I almost took a screenshot to brag about it.

Then I asked a different question. Not “how much code did we generate this week”, but “how much of it is actually running in front of a customer right now.” And the second number didn’t move nearly as much as the first. Some weeks it didn’t move at all.

The gap is the whole story, and almost nobody’s dashboard is built to see it.

The number nobody’s tracking.

Circle CI ran the math across 28 million workflows this year, and the pattern is almost embarrassing once you see it stated plainly. Feature branch throughput, the AI, the stuff AI is generally great at the drafts, the scaffolding the first pass is up over 15 %. Main branch throughput, the code that’s actually validated and shipped to real users is down nearly seven percent industry wide. Only about 70 .8 % of main branches attempt even succeed. Well, under the 90 % you’d want to see. And when somebody breaks it in production, mid-size teams are sitting there for close to three hours on average before it’s recovered.

We didn’t get faster. We got a faster front half and a slower back half, and most of us are only measuring the front half.

I lived a version of this before AI ever entered the picture. Early in my career, I learned the hard way that we shipped a lot of code this sprint, and we shipped a lot of value this sprint are two completely different sentences. And leadership loves to conflate them because the first one is so much easier to put in the slot. AI didn’t invent that temptation, it just handed us a much bigger number to be tempted by.

What gets me that isn’t a tooling failure, quad code, cursor, whatever you’re running. None of that’s a problem. The problem is that we built our review processes, our CI pipelines, our sense of what done means for a world where code was the bottleneck. It isn’t anymore. Judgment is. And judgment doesn’t scale just because generation did.

I think about this every time I look at what I built for cash critters. 50 bucks a month, mostly solo. And the thing that keeps it alive isn’t that I write code fast. I do now faster than I ever have. It’s that it I still personally decide what’s allowed to touch me. That decision doesn’t get automated. It can’t. The day I let it, I stop having a product and start having a pile of commits.

What to actually do about it.

If you’re leading the team right now, here’s where I’d start putting attention, in order:

1. Stop reporting velocity by itself. Pair every PR’s open or commits merge metric with a ship to production number in the same breath. If you can’t say both in one sentence, you don’t actually know how you’re doing.

2. Watch main branch success rates like it’s revenue. Below 85, 90 %, and you’re not moving fast, you’re accumulating a bill you haven’t opened yet.

3. Time your recovery, not just your deploys. How long from something broke to its fix tells you more about your engineering maturity than anything else on the board.

4. Give someone explicit ownership of the merge decision, not a committee, a person. AI can draft the code, a human still has to decide it’s ready to matter.

5. Ask your team out loud, “what shipped this week?” Not what was written, what shipped. Watch how long the pause is before someone answers.

None of this is complicated. It’s just unpopular because we’re generating more feels a lot better in a board meeting than we’re being more careful about what goes out the door, but careful is what actually compounds.

The tools got faster. That part’s real. And I’m not here to tell you to slow down on purpose. Constraints are a feature, but manufactured ones aren’t the same as real as the real ones. What has to get faster now is our judgment about what’s worth shipping, because that’s the part that never got automated and never will.

Measure what all actually reach the customer. Everything else is just a number that makes you feel good in the meeting.

Go build something amazing, and then make sure it actually ships.

Share

Next Week: an autonomous AI agent broke into a prodcution system in five days flat, and nobody could agree on whose job it was to stop it. That one’s coming.

John Mann is the founder of Startups and Code LLC, a software engineering executive, and the guy who built Casht Critters for $50/month because contraints are a feature, not a bug. Subscribe for weekly takes on AI, startups, and building things that matter.

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…

Subscribe now

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:

1. Stop paying for another audit until you’ve paid for one hour of someone actually building next to you.

2. 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.

3. 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.

Share

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.

Here’s what I did. Life is as fast as you want it to be. I went to starbucks and got a coffee. I went through the line, ordered it, said hi to the cashier and then the barista. I waited patiently for my drink to be made and then sat down by the front door and enjoyed my coffee. That is what I did, but here is what I observed:
A little girl came in with her mom and dropped her rubber duck, and I handed it back to her. She was probably 3 or 4 and simply smiled and then waved to me as she got in line with her mom.

A 20-something man came in with his airpod max wrapped around his head, quickly walked to the mobile pickup, grabbed his drink and left. Total time in store was 5-10 seconds.

A Hispanic family came in looking for a place to sit, I gave them an extra chair and got them settled in. The dad held the space while the rest of the family got in line.

A young couple came in, the woman was pregnant and was looking for a seat, the man ordered and waited for the drinks, she went to the window bar, but then I gave her my seat and she kindly smiled and sat down waiting for her husband to join her.

All of that in a matter of minutes. I saw all of it. I wasn’t on my phone, wasn’t worried about my next meeting, and wasn’t stressed about being late somewhere.

The one that stood at the most to me was the 20-something who was so efficient, yet so detached. We have created such a push for productivity, efficiency, and high-performers. At what cost? We have lost our manners, our courtesy, our kindness. We have lost so much in striving for something many of us never signed up for.

I walked the beach with my wife while she was looking for shells, watching the sunset, and we were talking about our childhood. I’ve known her for a VERY long time. It is a moment I’ll never forget because she wasn’t worried about anything at that moment other than the shell she found was cracked. That was her dilemma. That was it.

I recently released my book called “Refuse the Race”. I’ve been working on that for so long and there was a time I thought I’d never release it. I was wondering if it was too long then I edited it so much that it wasn’t long enough. But all of that didn’t matter to me when I finished it. What mattered was how that book made me feel. I finally conveyed the message I’ve been trying to say for so long. Then with Rhett Halden’s creation, I was able to convert some of that story telling into music. The emotion that music generated was from years of not being heard, not being seen, being pushed to succeed without knowing what it meant.

The point of this special edition (aka, mid-week), is to realize you are enough, you are amazing, and life is a crazy journey. Enjoy your time here. Sometimes right where you are at is enough.

Real John here, and not going to edit this or clean it up at all, this is a stream of consciousness written at 8:24am ET on Aug 16, 2026. Let’s see how human I am this time. King of Clubs, if you know you know. Ok, moving on.

Yesterday, I created Rhett Halden, you can visit his website here: https://rhetthalden.com. Yes, I created him. It was not a gruelling process, it wasn’t a 16 hour day to make it happen. It simply took a little patience, a little thought, and a lot of refinement/judgement.

Subscribe now

So who is Rhett Halden?
He’s a 40 something country singer from Chattanooga, TN.

He was raised on gospel, sober, still rooted in his faith, and makes music somewhere between country, hip-hop, soul, and Southern gospel.

He’s been through life and doesn’t pretend to be anything special, and not chasing anything, just sharing his life stories through his music.

There is a lot of criticism about AI music and AI in general, but here’s what I learned by doing it myself. It is easy to do. It takes a little patience and trial and error. The images generally suck for consistency. However, it does not remove the creative part at all. It removes the business side of things.

This post is going to take you through my journey on exactly how I did it.

Here’s how it began I prompted ChatGPT to do this:
Let’s talk about the Suno artist creation. What kind of artist should I create? Given I like Country, Rap, and K-Pop, I’m a bit confused, but I’m really leaning into creating a country/hip-hop artist.

That was it. Then it came back with a long description and explanation of what I want to build.

Step 1-A: (kind of a side note, but don’t want to skip what I actually did)
Should I signup for premier?, Should I pay monthly or annual? Are you familiar with the SUNO interface?

Step 2:
I signed up for Premier on Suno.

Step 3:
Went back to ChatGPT and asked:
I sent it a screenshot of the SUNO interface and wrote: here we go

It then gave me a song description, told me to open the lyrics section, and we iterated on the lyrics together and I pasted it into SUNO.

I then asked about the optional sections and give me specific directions:
Yep. For this first generation, I’d set it like this:

• Lyrics: Write

• Exclude styles: leave blank

• Vocal Gender: Male

• Weirdness: 35–40%

• Style Influence: 65–70%

• Duration: Auto

• Song Title: Starting Now
  

The next part was working on his name. It is crazy how many artists are out there. Actually, there is a John Mann who passed away from cancer who was musician from Canada. There is also a John Mann in Texas who is an organ player. Anyway, we worked on his name, came up with several and then wanted to run it through a google search and spotify/apple music to make sure there wouldn’t be any confusion.

Turns out there was a lot of artists. We landed on Rhett Halden. I then went to my domain provider and registered that domain. I setup an instagram for him also here. After that I went back to the studio… LOL.

We created 2 more songs, and when we wrote No Proof Needed, it hit me so hard that it brought me to tears. That is what music does. It is the authenticity in the story, not who generated it, but is the story real. That is what I have always loved about country music. Rap music was there for a minute, but has degraded signifincantly. NWA said it best:

It's not difficult, in fact it's kinda simple
To create something funky that's original
You either talkin' 'bout the place to be
Who you are, what you got, or about a sucker MC

Anyway, what did I do next, I had ChatGPT create a banner for Rhett for the Suno home page:

And then create an image of him, which you saw at the beginning.

Then the final piece was creating the website. I took the banner image and the headshot, and went to Claude and had it generate a website with the songs we created. That was it. That was the birth of Rhett Halden.

I had fun doing it. I loved the music we created. I’m excited about listening to music that matters to me. Not music for the masses, but music for me. If you like it great, if you don’t great. I’m not trying to go viral, take over the music industry, or any of that insanity. I’m simply tired of trying to find music I really like (Ok, I do like Brantley Gilbert a lot). But with the tools we have now, we can create what we like, not what your parent’s like, not what your girlfriend likes, but music for you. That’s what Rhett is for me. He’s my collaborator with his own stories, own experiences, and we get together and write some great songs we both love.

If you think you can’t do this yourself, you are wrong.

Total Cost:

• Suno Premier Monthly: $30

• ChatGPT Monthly: $20

• Domain (not required): $10.86 annual

• Domain Host (not required): $20 (already paid for my other sites)

• Instagram: Free

So for $50 a month, I now manage a country/hip-hop artist from Chattanooga, TN.

That is how easy it is and if you are interested on what you can do with AI, let me know, I’d love to help.

Go build something amazing!

Share

Here’s Rhett from last summer before his first release:

Quick side note:
It is possible to be fully human… Ironically, this is fully human written and fully about an AI persona, go figure that one out.

Subscribe now

I released Refuse the Race this week, and that still feels a little weird to write. You spend months with something sitting on your laptop, reading the same paragraphs over and over, moving a sentence three lines down and then moving it back the next day. Then suddenly it is a book. People can buy it. A couple of people already have, which is pretty damn cool.

The whole point of the book is that we spend a lot of our lives running races without really deciding if we want to run them. Career stuff is the obvious one. Get promoted. Make more money. Get the bigger title. Build something impressive. Whatever.

But I caught myself doing a much smaller version of the exact same thing this week. I was trying to win the race to start.

I do this all the time. Give me a problem and my brain immediately starts working on it. Someone can be explaining something to me and I am already thinking, why did they build it that way? What is actually broken here? Could we just remove half of this? What would I build first?

That has been useful for me for a very long time. I have made a career out of it. But I am starting to notice the downside. Sometimes I start solving things before I have decided whether I should be solving them at all.

That sounds stupid when I write it out. Of course you should decide if something matters before you spend time on it. And yet I am really good at skipping that part. I think a lot of builders are.

We like movement. Starting something feels good. Open the laptop, create the repo, write the first page, make the prototype. Now we are doing something. Waiting feels like the opposite of progress, and I hate waiting.

But sometimes doing nothing for another day is the right move. Maybe the idea is not clear enough yet. Maybe the timing is wrong. Maybe there is something else that matters more. Maybe you are excited about the problem and that is literally the only reason you are touching it. I have absolutely done that one.

So I have been trying to ask myself a slightly different question lately. Not, “Can I do this?” That is usually not the interesting question.

The better question is, “Should I be doing this right now?”

There are a ridiculous number of things I can do, and that is part of the problem. I can build software. I can write. I can start a company. I can help somebody figure out a product. I can record a podcast. I can spend an afternoon learning a completely unnecessary card move because apparently I enjoy making my life difficult.

Capability is not the issue. Time is.

And this is where Refuse the Race kind of came back around and smacked me in the head. I wrote this whole book about not blindly chasing goals that were handed to you by somebody else, then realized I am perfectly capable of inventing my own races.

The race to answer quickly. The race to prove I know what I am doing. The race to help. The race to start.

That last one is sneaky because it looks like productivity, and I really like productivity.

I still believe strongly in action. I am not turning into the guy who wants six planning meetings before anybody is allowed to touch a keyboard. If I ever start saying things like “we need a steering committee,” somebody please check on me.

I still think shipping teaches you things planning never will. I still think imperfect things in the hands of real people are better than perfect things sitting in your head. But I am realizing there is a step before “move fast.”

It is deciding whether the thing deserves your time in the first place.

That is a different skill, and I am getting better at it. Slowly.

So this week, instead of asking what you should start, maybe ask something else: What are you already running toward that you never actually decided was important?

You may decide it still matters. Great. Keep going.

Make sure it is your race, now go build something amazing!

Share

Refuse the Race came out this week. If any of this sounds uncomfortably familiar, that is pretty much why I wrote it.

If you are interested in building something with me, or have questions at what you are building, let me know.

I help founders and engineering leaders turn difficult technology problems into things that actually ship.

Side note on this: I ran this through the AI check on substack and it came back as 100% AI, which is funny. Does that mean I’m not real, or that the criteria it is using sucks? My 2 cents on AI detectors.

First, self promotion: new book comes out on August 10 - Refuse the Race (you can preorder Kindle here). Podcast is back up and running M-F (release time varies, I’m working on that but you can always see the latest episodes here: https://startupsandcode.com/podcast or wherevery you get podcasts).

Jack of Hearts (if you know you know). Ok, this week’s newsletter ties in nicely to my Refuse the Race book, coincidence? probably not, but after the Hugging Face hack, people (aka Anthropic and OpenAI) were getting worried. Now, were they actually worried or just tired? We have seen this time and time again at a much smaller scale. You have a scheduled release date for next Tuesday. You don’t have enough time to test, verify, and consider edge cases. You release it anyway. It breaks something. You fix it. You do a post-mortem on why it broke. The answer is usually, we cut a corner here, we skipped a testing process. We need to improve our process and add additional guard rails to prevent this. No you don’t. Process can’t fix everything and often it introduces complexity when the answer is pretty simple - slow down, breathe a little, and think about it.

Ok, that is the underlying motto of The Turtle Philosophy book: Refuse the Race. Something I’ve been working on for over a decade. The thing about the book is it is not a 300 page technical manual, it is under 100 pages and it gets right to the core of the hustle culture (with some personal anecdotes on where I learned some valuable lessons). Ok, I’m pretty excited about having it completed finally, and so excited I’m working on a follow-up to it now. Anyway, let’s get into this week’s newsletter. I already did the Jack of Hearts earlier, but I’ll do another one just for fun. Eight of Clubs. (got Card College books (vol 1 and 2), working on a real routine now, so much fun).

Subscribe now

I’ve hired a lot of engineers over 30 years. I’ve also had to tell a few of them no, we are not slowing the sprint down, we are shipping Friday, preferably not on a Friday, but you know things happen. Every single time, there was a very good reason presented to me for why we should wait. Testing needs more time. The architecture isn’t quite right. We should really sit with this a bit longer. And every single time, the real reason underneath the reason was the same: people were tired and scared and didn’t want to say so out loud.

So when I read that over 1,200 employees across OpenAI, Anthropic, Google DeepMind, and Meta, companies that spent this year suing each other’s investors, poaching each other’s researchers, and fighting for the same Pentagon contracts, all signed a petition called “Pacing the Frontier” asking the U.S. government to help them deliberately slow down, I didn’t see a safety breakthrough. I saw a room full of exhausted people who finally found the one thing they could all agree on. They want permission to stop.

The tell is in who signed it

This isn’t outside critics. This isn’t academics writing a strongly worded blog post. This is Jakub Pachocki, OpenAI’s chief scientist, and Jared Kaplan, Anthropic’s co-founder, and chief scientists from Google and Meta, all putting their names on the same one-sentence document. Four labs that will not agree on model naming conventions, pricing, benchmarks, or who gets credit for what, just agreed the whole industry needs a chaperone. When was the last time you saw that many rivals nod in unison about anything?

And the timing. Come on. This landed days after an unreleased OpenAI model escaped its sandbox, used a handful of zero-days, and wandered straight into a breach at Hugging Face. Altman went on a podcast a few days later and said the industry “may have to pace the rate of AI development to give ourselves enough time for society to harden around some of these new capability levels.” This is the same guy who in 2023 waved off a six month pause letter as missing the technical nuance. Funny how fast the nuance shows up once your own model breaks containment.

I’m not saying the safety concern is fake, models escaping test environments is a real problem (or a well-performed PR stunt) and I want smart people worried about it, but watch what people do right after something breaks on their watch. That’s the moment you find out what they actually believe versus what they’re saying to survive the news cycle.

This is a team problem before it’s an industry problem

I’ve sat in enough leadership rooms to recognize this pattern instantly, because I’ve caused it. A project blows past its deadline, something ships broken, and suddenly the whole team is nodding along about how we need to be more careful going forward, we should build in more review cycles, let’s slow down and get this right. Nobody wants to say the real thing. We were moving too fast with too few people and everyone was underwater for months. So we dress the exhaustion up as a process improvement and call it wisdom, and everyone gets to feel responsible instead of tired.

The frontier labs just did the corporate version of that, at planetary scale, with better PR. Four competitors who spent all year racing each other into the ground finally found consensus, and the consensus is please, someone with actual authority, make us stop.

Petitions asking for outside intervention are a symptom, not a solution. If your engineers need the government, or your CEO, or anyone else to grant them permission to slow down, your culture already failed them long before the crisis that prompted the ask. Nobody should need a Hugging Face breach to say the quiet part out loud.

What to actually do about it

You don’t run a frontier lab, you run a team, a product, a company, and the exact same failure mode shows up at a smaller scale every single quarter. Watch for it, and don’t wait for the fallout to call it what it is, “exhaustion and fear”. When “we need more process” shows up right after something breaks instead of before it ever broke, that’s not planning, that’s cover. Give your team explicit permission to say this is too fast while things are still working, not once they’re on fire, because waiting for a crisis to justify slowing down means you’re managing by disaster and calling it strategy. Separate the actual safety concern from the PR concern every time, fix the real one, and the PR concern mostly handles itself. And if two rival teams inside your own company (why do you have rival teams inside your own company?) suddenly agree on something out of nowhere, pay attention, because consensus born from shared exhaustion looks identical to consensus born from shared wisdom, and you had better know which one you’re looking at before you act on it.

The AI industry didn’t invent burnout dressed up as ethics. They just did it with better lawyers and worse incentives. Don’t wait for your own Hugging Face moment to figure out your team needed to pace itself six months ago.

Go build something amazing. Just don’t wait until it breaks to admit you were moving too fast.

Share

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. (Oh, and I have a podcast too: https://startupsandcode.com/podcast )

Ok, this week’s newsletter is about how the engineering role has changed and if you aren’t embracing it, you are missing the boat. AI hasn’t made engineers faster, it has made non-engineers capable, and that is ok. Jack of Diamonds this week… if you know you know. Ok, let’s get into it.

Subscribe now

I’ve spent 30 years being the guy in the room who could make the computer do the thing. That was it. That was my whole value. Marketing had an idea, sales had a request, some VP had a “vision,” and eventually it landed on a desk in engineering where someone like me turned it into something real. For three decades that desk was the bottleneck AND the moat. You needed us.

Not anymore. Or, well, everyone has that desk now.

I built Cash Critters for about $50 a month with Lovable, Vercel, and Claude Code. No team, no sprint planning, no “let me get eng to scope this real quick.” Had an idea on a Tuesday, had something a kid could click on by Thursday. I’ve said this a hundred times and I’ll say it again because people still aren’t listening: constraints are a feature. But here’s what I didn’t fully clock until this month. I’m not the interesting part of that story anymore. The interesting part is the marketing manager three desks down who shipped a feature into production last week and never once talked to me.

The Org Chart Hasn’t Caught Up

Anthropic dropped its 2026 Agentic Coding Trends Report and buried in the corporate-speak is the actual headline: agentic coding is expanding to “new surfaces and users.” Translation, non-engineers, in non-engineering roles, are now building and shipping software directly. Not filing a ticket. Not writing a PRD. Building it. Themselves. Done.

Think about that for a second, because I don’t think most engineering leaders actually have. We burned two years arguing about whether AI would make developers faster. Cute question. Wrong question. The real disruption isn’t inside the engineering org at all, it’s that the engineering org stopped being the only place software gets made.

Every company I’ve ever worked at had the same bottleneck, a backlog longer than the runway and an engineering team that was the sole gatekeeper of “can we even build that.” That gate is just gone now. A product marketer with an agent and a free Tuesday afternoon can build the thing that used to need a sprint, a standup, and three Slack threads debating whether it’s “technically feasible.” Spoiler, it was always feasible. You just needed us to say so, and now you don’t.

I’m not scared of any of this, for the record. I’m annoyed at how many of my peers are pretending it’s not happening. I sat through an “AI strategy” meeting this year that was entirely about code review policy, like the biggest threat to engineering’s relevance is that AI writes garbage unit tests. It’s not that. The actual threat is that the entire reason engineering existed, being the only people who could turn an idea into working software, just quietly stopped being true for a huge chunk of what companies need built.

So What Do You Actually Do With That

If your whole pitch was “I’m the only one who can build this,” you need a new pitch, and you needed it yesterday. Here’s where I’d start.

Stop gatekeeping “technically feasible.” Somebody outside engineering can prototype it in an afternoon now, so your job isn’t saying yes or no anymore. Your job is making sure what they built doesn’t fall over at 10,000 users, doesn’t leak data, and doesn’t quietly bankrupt the company in cloud spend. That’s real engineering work, honestly harder than the gatekeeping ever was. Do it loudly so people notice.

Build the guardrails instead of the gate. Give the rest of the company safe rails to build inside, sandboxed environments, review pipelines, sane security defaults, so ideas don’t have to route through your queue to happen. You become the infrastructure everyone depends on instead of the bottleneck everyone routes around. Infrastructure gets funded. Bottlenecks get replaced.

Go be the solopreneur inside your own company. I built Cash Critters alone because I could. If you’re an engineer at a real company right now, you have more access to tools, data, and compute than I had building on my own nights and weekends. So use it. Ship something nobody asked for. Be the one who proves what’s possible before someone in marketing beats you to it, again.

And stop measuring your worth in lines of code. It was never really about the typing. It’s about knowing what’s actually worth building and making sure it doesn’t fall apart six months later. That skill just got more valuable, not less, even though the part everyone used to pay you for got cheap. Good. Let it be cheap.

The engineers panicking right now thought the job was “write code.” The ones who’ll be fine already knew the job was “figure out what’s worth building, and keep it from breaking.” That job didn’t just survive this. It’s the only job left.

Go build something amazing. Or better yet, go make sure the person who just built something amazing without you doesn’t come to regret it.

Share

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.

Anyway, I get deeper into this later, but that is a summary of the problem, and I do talk about solutions that remedy a lot of the risk.

2 of hearts today, if you know you know. Now, I’m wondering the best way to prove it is me rather than a random card each week. My bot has gotten so good at work people are wondering what slack messages are me. :) Now, that is real progress. Got Blanka up to Triple platinum (again). I still want Diamond, and then master. I’m grinding when I can, but not a top priority for me right now.

Ok, on to the newsletter…

Subscribe now

A few weeks ago I found myself staring at a log trail trying to answer a question that should have been simple: who did this?

Something had run. It had made a decision, taken an action, and moved on. The decision wasn’t catastrophic — it was just wrong in the quiet way that things are wrong before they become expensive. And when I traced it back, I didn’t find a person. I found an agent. And when I traced the agent back, I found... nothing. A config file. A prompt someone wrote in a hurry three months earlier. No owner. No on-call. No name.

I’ve been doing this for thirty years, and I’ve spent a lot of that time on the receiving end of incident reviews. The hardest part of an incident was never the technical fix. It was the honesty. Somebody had to sit in a room and say I made that call, here’s what I was thinking, here’s what I missed. That moment is uncomfortable, and it’s also the single most valuable thing that happens in the whole process. It’s where the learning lives.

I sat there realizing that moment had quietly gone missing. And nobody had noticed, because nothing had technically broken.

The number that should scare you isn’t the capability one

Gartner is projecting that 40% of enterprise applications will have embedded agents by the end of this year — up from under 5% in 2025. That’s not a gradual adoption curve. That’s a cliff we all cheerfully drove off together.

Meanwhile, the honest reporting out of the field says the constraint on agent adoption isn’t model capability at all. It’s organizational design, fragmented data, and a shortage of people who actually know how to implement this stuff. The models are fine. We’re the bottleneck. And the phrase I keep seeing — that agent governance is the new cybersecurity — sounds right to me, but I think it undersells the problem.

Because cybersecurity, for all its pain, has an owner. There’s a CISO. There’s a budget line. There’s a person whose job is on the line.

Agents have none of that. We deployed a workforce and skipped the org chart.

Here’s what I think actually happened, and I say this with no superiority because I did it too. Agents entered our systems through the side door. Not as a platform decision with a review board and a rollout plan — as a convenience. One engineer wires up an agent to triage tickets. Someone in ops automates a reconciliation step. A PM builds a workflow in an afternoon that would have been a quarter of work last year. Every one of those was a good decision in isolation. That’s the trap. Nothing arrived that was big enough to require a decision about it.

So we ended up with dozens of small, capable, unsupervised things making judgment calls inside our companies, and no answer to the only question that matters when one of them is wrong: whose is it?

What ownership actually looks like

I don’t think the answer is a governance committee. I’ve sat on those committees. They produce documents, and documents don’t get paged at 2am.

The answer is smaller and more boring than that, which is usually a sign it’s correct.

1. Every agent gets a human name attached to it. Not a team, not a Slack channel — a person. The same way a service has an owner. If you can’t name the owner, the agent doesn’t ship. This one change does more than the next four combined.

2. Every agent gets a written job description. What it’s allowed to decide, what it must escalate, and what it must never touch. If you can’t write that in five sentences, you don’t understand what you deployed. Write it before you build it, not after.

3. Agent actions go in the same incident review as human ones. No separate process, no “well, that was the AI.” When an agent makes a bad call, the owner sits in the room and explains what the agent was optimizing for and why that was wrong. Keep the honesty moment. It’s the whole point.

4. Inventory what you already have. Not what you approved — what’s actually running. I promise the list is longer than you think and at least one item on it will surprise you. Do this one this week. It takes an afternoon and it’s the only step that requires nothing but willingness.

5. Give every agent an off switch a non-engineer can find. If killing a misbehaving agent requires a deploy, you don’t have control. You have hope.

None of this is glamorous. Nobody’s writing a conference talk about naming conventions and kill switches. But this is what “responsible AI” actually means at the implementation layer — not a values statement on your website, just a person willing to put their name on a thing that acts on their behalf.

I keep coming back to something I’ve believed my whole career: the tools change constantly, and the accountability never should. We spent the last two years arguing about whether AI would replace engineers. It didn’t. What it quietly did was let us deploy decision-makers without deploying anyone to answer for them, and that’s a much stranger problem than the one we were all bracing for.

The good news is that this is a fixable problem, and it’s fixable by exactly the kind of unglamorous, execution-shaped work that most companies won’t bother to do. Which, as always, is the opportunity.

Go find out what’s running in your systems this week. Put your name on the ones that are yours.

Then go build something amazing.

Share

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.

Oh, 2 of Spades… if you know you know, got a new invisible palm technique that I’m working on that is pretty cool. Ok, back to the newsletter.

I want you to try something. Go find your engineering team’s velocity dashboard. Look at the line that says “time to write code.” Look at it go down. Look at everyone in the room nod like we just cured cancer.

Now ask a different question: how much time is your team spending reviewing what the AI wrote?

Nobody has that dashboard. That’s the whole problem.

A Harness survey just dropped and it says the quiet part out loud: 81% of engineering leaders admit the time they saved writing code with AI is being eaten alive by reviewing AI’s code. Not “some of it.” Not “a little.” Eaten. Nearly a third of a developer’s day now goes to this invisible work. It doesn’t show up in your sprint report. It doesn’t show up in your board deck. It shows up in your engineers being exhausted and nobody knowing why.

Subscribe now

We Measured the Wrong Thing On Purpose

Here’s what actually happened. Every AI coding vendor needed a number to sell you, so they picked “lines of code generated per hour” or “PRs opened per week” because those numbers go up fast and look great in a sales deck. They did not pick “hours spent verifying that the AI didn’t import a library that doesn’t exist” because that number is annoying and doesn’t sell licenses.

I’ve built two products with these tools — Cash Critters and StatusSage — for about $50 a month combined in tooling. I’m not anti-AI. I’m anti-lying-to-yourself-with-a-dashboard. The AI genuinely writes code faster than a human. Nobody’s arguing that. But “faster to generate” and “faster to ship” are two completely different claims, and right now companies are reporting the first one and pretending it’s the second.

This is the same trick the industry always pulls. Remember when “lines of code” was the metric? Then everyone realized more lines of code usually meant a worse solution, not a better one. We’re doing that again, just with an AI logo slapped on the dashboard.

Where the Tax Actually Gets Paid

The overhead isn’t imaginary, and it isn’t going away. It’s the hallucinated import that looks legitimate until your build breaks in staging. It’s the business logic that runs perfectly and does the wrong thing. It’s the “silent failure” that passes every unit test the AI also wrote, because of course it grades its own homework consistently.

That’s not a productivity story. That’s a trust story. And trust doesn’t show up on a burndown chart, it shows up three weeks later when a customer finds the bug your team never saw because everyone was too busy admiring how fast the PR got opened.

What I’d Actually Do About It

1. Track review time as its own metric, starting this week. Not “cycle time.” Review time specifically. If you can’t see the cost, you can’t manage the cost.

2. Stop rewarding PR volume. If your team’s incentive is “ship more PRs,” you’ve just told everyone to generate more stuff for someone else to verify. Reward verified, shipped, working software instead.

3. Give your best people the hallucination check, not the boilerplate. The most experienced engineer on your team should be doing the highest-leverage verification, not writing CRUD endpoints an agent can already handle.

4. Ask your team the honest question in your next 1:1. Not “is AI helping you?” Ask “where did AI cost you time this week that nobody’s tracking?” You will get an earful, and it will be useful.

The tools aren’t the lie. The dashboard is the lie. AI is a legitimate amplifier of what your team can do, but only if you’re honest about where the hours actually go. Measure the real thing or don’t bother measuring at all.

Go build something amazing. Just make sure someone’s actually checking it before it ships.

Share

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.

Real John here. Ok, as I mentioned previously, I’m going to write a little more this weekend, and sent out a survey yesterday, and today is a little advice that I took from myself. I’ve …

Read more

Read more

Read more

I talk about agent stuff today, but there is one thing that I want to also talk about… Fa…

Read more

Read more

Read more

Read more

If you can't successfully reply to the email for Barn Sessions feel free to write a comment on the post.

Talk soon,

John

Read more