Stories and insights from our journey building profitable SaaS products
Email is the tax you pay for running a company. Not the writing, the writing is the easy part. It is the standing start. Open the inbox, reconstruct who this person is, remember what I promised them three weeks ago, find the last thing I sent them, decide whether this even needs me, and only then write four sentences. Forty times a day. The reply is nothing. The runway to the reply is everything.…
At AI week, Gian Segato from Anthropic said something offhand that I have not been able to put down. He mentioned that a lot of people inside Anthropic keep their own personal eval for Claude. Not the big public benchmarks. A small, private test, tuned to something they personally care about, that they trust more than any leaderboard to tell them whether a new model is actually better. That one…
There is an idea going around right now that I cannot stop thinking about: the self-improving company. Tom Blomfield laid out the clearest version of it in a Y Combinator talk , and AI Jason has a good, practical companion to it on building proactive, self-improving agents . I want to write down what landed for me, because it is the direction I am already building FlatNine in, and putting it into…
This is the third post in a series about FlatNine Intelligence. The first was about the news feed (reading the world at macro scale), the second about Launches (catching new products the moment they go live). This one is about the third sibling: Dev , a feed of what is actually climbing on GitHub right now. I build software for a living, so a real part of my job is keeping up with the tools. Which…
This is the second post in a series about FlatNine Intelligence. The first was about the news feed , a system that reads the world at macro scale. This one is about its sibling: Launches , a feed that catches new products at the exact moment they come to life. I build small software for a living, and I back a little of it too. Which means I am endlessly, slightly compulsively curious about what…
This is the first post in a series about FlatNine Intelligence, a platform I have been building to read the world at macro scale. This one is about the part I needed most: the news feed at intelligence.flatnine.co/news . I have a confession that is a little embarrassing for someone who builds software for a living: I cannot keep up with the news. Not the headlines. The headlines are the easy part,…
A few days ago I posted this: Basically every person that ever messages me for a bit now gets profiled so I can improve how I can talk with them. 👀 The replies split neatly into two camps: "this is genius" and "this is deeply unsettling." Both reactions are fair. So here is the longer version: what I actually built, why I built it, and where I think the privacy line sits. The itch I talk to a lot…
I run multiple products. Alone. The only way that math works is if monitoring is not a thing I do. Last quarter I built a monitoring platform, which I usually just call flatnine-health: the single dashboard for every metric across every FlatNine product. Heartbeats, application errors, uptime checks, slow pages, database metrics, server metrics. Everything that used to live in five different…
If Google links websites, what links AI agents? Right now, nothing. When I run agents that call other agents, the connection is invisible. Agent A invokes Agent B. They swap tokens, do the work, return a result. Nobody outside the call knows it happened. There is no record an outside party can verify. There is no graph forming. That is the whole problem. Google's real moat was never the links It…
Every AI agent system I have seen works the same way. You talk to it. It does something. It stops. That is fine for a chatbot. It is not fine for a system that runs your business. I run 18 AI agents . They learn from the web , pitch me ideas , evaluate their own work , and even dream at night . But until now, they only worked when triggered. A cron job fires at 07:00, agents learn. Another fires…
Most AI agent systems have a fatal flaw: the human is the bottleneck. You build agents, give them tools, define their roles. Then you spend your entire day deciding what they should work on. You become a full-time manager of robots. I run 18 AI agents across my business. Security, marketing, sales, content, infrastructure, health, even music. Each one has domain expertise. Each one has tools. But…
I've been building an AI agent system called FlatNine Ensemble , a team of 20 specialized AI agents that run my business and personal life 24/7. Recently, I connected them to the physical devices in my home. Here's what happened. The Setup My home in Puglia (the heel of Italy!) has a 16.5 kW solar panel system with a 20 kWh battery, 8 security cameras, smart thermostats, a Google Nest Hub, and…
Running 18 AI agents across an organization sounds impressive until you ask: how do you know they are doing a good job? We have been building FlatNine Ensemble - a system where AI agents handle everything from security monitoring to content creation, from SEO analysis to customer support. Each agent learns, proposes work, and executes tasks autonomously. But autonomy without accountability is just…
Most AI agents sit idle until you talk to them. They wait. They respond. They forget. This is fine for a chatbot. It is not fine for a team. I run 18 AI agents. They handle security, marketing, sales, content, infrastructure, health tracking, even my jazz gig calendar. Each one has a domain. Each one has tools. But until last week, none of them learned anything on their own. They only knew what I…
Most AI assistants forget you the moment the conversation ends. They have no yesterday. No last week. No memory of what you decided three months ago. Every interaction starts from zero. This is fine for "summarize this PDF." It is not fine when you are trying to build an AI that actually knows you. I have been running an AI agent system for over a year now. 18 specialized agents that handle…
Most agent frameworks today are just corporate org charts with an API layer on top. CEO agent delegates to manager agents. Manager agents delegate to worker agents. Someone calls it "orchestration" and ships it as a framework. But that hierarchy is a human constraint. It exists because humans have limited attention spans and communication bandwidth. A VP can only manage so many direct reports. A…
Here is a formula for work: $$t_w = t_{exec} + \frac{n_h(n_h - 1)}{2} \cdot \frac{\tau}{\phi}$$ Most people have never seen this written down. Most people have never even thought to ask the question. But if you run a business and your time is a real input, this equation is the most important thing you are not measuring. Let's unpack it. First, a Scope Check: This Isn't About Passive Investment…
SaaS was built on a lie we all accepted because there was no alternative. The lie: everyone gets the same product. Same interface. Same dashboard. Same color scheme. Same insights, framed the same way, for a logistics company in Milan and a marketing agency in Austin and a solo consultant in Lisbon. You segment by plan tier, maybe by role, and you call that personalization. It was never…
Every AI agent framework today is obsessed with doing. Write this email. Scrape this page. Deploy this code. Generate this report. Nobody s building agents that think. I don t mean "think" as in chain-of-thought reasoning before answering a question. I mean agents that proactively analyze the state of your business, notice patterns you re missing, connect dots across domains, and surface strategic…
Folks, as you know I currently run a human-free business. All of my team members are AI agents. Each role has an AI agent who takes care of different tasks. This is an ongoing series where I present each one of my AI team members to you. Today we are presenting, Carla, my AI Chief of Staff. 👨🏻🏫 Meet Carla: AI Chief of Staff Imagine having a right-hand assistant who never sleeps, knows your…
Just a list of things that, as of mid-2025, feel “obvious”— not because everyone is doing them yet, but because the writing is on the wall, and most people who are paying attention see them as inevitable (or at least, the next logical step): 1. AI Agents Will Eat Mundane Knowledge Work Everyone is using, or talking about using, AI agents to handle scheduling, customer support, basic research,…
1. True AR Glasses / “Spatial Computing” for the Masses Where We Are: Not Obvious Yet: But… 2. Universal Basic Income (UBI) or Social Wage Where We Are: Not Obvious Yet: But… 3. Four-Day Workweek as the Default Where We Are: Not Obvious Yet: But… 4. Widespread Cross-Company Data Sharing (“Open Data”) Where We Are: Not Obvious Yet: But… 5. Mainstream AI Companions Where We Are: Not Obvious Yet:…
As of today, I’m the last human in my team. I replaced all of my teammates with AI agents. So, first thing, what are AI agents? Is an agent something like this: Probably not. That’s just a n8n workflow: a glorified reproducible, shareable software function. Just a bunch of if/else conditions. For me, an agent is an autonomous process that is capable of learning and deciding what steps to take. So,…
A stoplight only has 3 states: Red : The stoplight is red, meaning vehicles must stop. Yellow : The stoplight is yellow, meaning vehicles should prepare to stop. Green : The stoplight is green, meaning vehicles can go. Transitions: Red to Green : The stoplight transitions from red to green after a predefined time (e.g., 60 seconds). Green to Yellow : The stoplight transitions from green to yellow…
TL; DR: This year was even worse than 2024 Generally speaking, 2025, as 2024, for me was all about having: The mind of a businessman The soul of a musician The body of an athlete While I think I improved towards each of these aspects, I failed all the goals I wanted to hit. I do feel like in 2025 I wasn’t centered. PERSONAL I moved to Portugal in June 2022, so this year marked my second year as a…