Here will be centralized all the old and current posts and thoughts, with tips and some solutions that I have implemented throughout my career.
Without explicit contracts, each agent invents its own interface. The result? Systems that work alone but break together.
The most underrated section of any RFC is 'out of scope'. For AI agents, it's the difference between a useful result and three hours of rework.
Every section of an RFC has an exact mirror in the world of prompts. Once you see the mapping, writing prompts becomes second nature.
Every RFC that works has six essential pieces. If you know how to assemble them for humans, you already know how to assemble them for AI agents.
The same discipline that makes an RFC work for human engineers is what makes a prompt work for AI agents. Most developers already have this skill - they just haven't realized it yet.
Why Monday morning reveals everything about your soul, why routine is your friend but monotony kills you, and the difference between being a robot and being an author of your own work.
How the Tick-Tock strategy I learned while working at Woovi ensures you can evolve your software without breaking anything. Applied to database changes, feature evolution, and APIs.
Researchers discovered that shuffling words 50 tokens ago doesn't change predictions at all. This insight led to architectures that are 23% leaner and 30% faster. Here's how treating distant text like blurry peripheral vision changes everything.
MIT researchers built an AI model that beat Google's 250 GPU-year monster while emitting less CO2 than your morning coffee. Here's the story of how brains beat brute force.
I spent the week playing with ClawdBot and I get the hype. It genuinely feels like having Jarvis. But we need to talk about the risks of running an autonomous agent with full access to your machine.