Your product team just spent two weeks crafting the perfect AI feature spec. Beautiful diagrams. User stories that would make a PM weep. They slide it across to engineering with that satisfied smile that says, "we've thought of everything." Engineering reads it. Engineering

Remember when I said your senior engineers should be a big part of discovery? Here's what actually happens when they are. They run experiments. Ugly ones. Fast ones. Brutally honest ones. And that's precisely why it works. See, engineers have a superpower that nobody talks

So, last week, I accidentally ran a sociology experiment on my own feed. I posted two types of content: the usual AI hot takes, and some unglamorous lessons from shipping actual LLM projects in production. You know, the stuff with scars and invoices attached. The results?

When LLMs emerged, we spent days in a room designing the perfect conversation VUI flow for our new AI assistant. Every possible user intent mapped. Every response crafted. Every edge case covered. Then we started building it. By day two, we realized our beautiful flowchart was

Let's be honest, your AI's personality probably sounds like a hostage reading a script written by your legal team. Polite? Sure. Helpful? Technically. Engaging? About as much as a tax form. It's okay. We've all been there. We once wrote an AI Constitution with a persona

My #1 rule for AI security, learned after burning through a frankly embarrassing number of tokens: Trust No User. The moment I'll never forget: watching our perfectly crafted AI assistant start writing detailed emails as the CEO. Not because we gave it email access, but because

Imagine your AI just gave investment advice that would make your lawyers weep. The user didn't even ask directly. They mentioned "reinvesting profits" and your helpful AI channelled its inner Warren Buffett. Your guardrails? They politely suggested the AI shouldn't do that. The

I tried to be cutting-edge and create an AI video for my posts. Instead, I created evidence that we're living in the 'expensive beta test' era of content creation. The AI took my money and ran. Here's the expensive disaster. ...and you can watch my financial crime scene attached

The AI experts promised LLMs will run your business while you sip margaritas on a beach. Will it make you $1mil? Anthropic just ran an experiment we've all been waiting for. Claude ran a vending machine at their HQ. Did it work? Well, it started selling products at a loss and

Back in the wild west days of early GPT-3.5, we built an AI assistant with a very specific, disagreeable personality. Think Dr. House, but for startup customer support. It was designed to be sharp, focused, and a little bit prickly. Predictably, users immediately started poking

Your AI thinks a conversation is a photograph. It's actually a movie. That single distinction is costing you customers and revenue. Let me explain. A static prompt, even one with history, forces your AI to act based on a single snapshot taken at the start. It's blind to the

Your AI thinks a conversation is a photograph. It's actually a movie. That single distinction is costing you customers and revenue. Let me explain. A static prompt, even one with history, forces your AI to act based on a single snapshot taken at the start. It's blind to the

The simple way to control complex AI conversations. If you've ever tried to guide an AI through a multi-step workflow, you know the pain. You end up building a fragile monster of chained prompts, separate LLM calls, and a nightmare of state management. It's slow, expensive, and

Who else is coming? 👀 If you're there, reply or DM me, would love to meet up.

I had to write a particularly emotional note to a friend today. And it's been a very difficult task for me. I won't lie and say I wasn't tempted to use AI assistance. I was. I always found it hard to write. Write anything really. AI helps me with that. But there is a line I'm

Nie czytam wiele książek, ale na jedną jednak czekam. Bo wiem, że rozwijanie firmy usługowej na globalnym rynku to nie lada wyzwanie. the5.tech

Planets are aligning at OpenAI . Thoughts on a napkin after attending DevDay 2025 People in the #VoiceFirst world all remember how hard it was for Amazon and Google to get the experience right with Alexa and Assistant. Discoverability and monetization were never really solved

Discoverability is the new search. It was always the Achilles’ heel of conversational platforms. Neither Alexa nor Google Assistant ever solved it. The challenge is simple to describe, yet brutal to solve: 👉 How do you help a user find or provide the right thing in a world