Here will be centralized all the old and current posts and thoughts, with tips and some solutions that I have implemented throughout my career.
A single document that works as an RFC for engineers and as a prompt for agents. It's not a compromise - it's the better version of both.
RFCs assume the reader knows the project. Agents know nothing. Externalizing implicit context is the difference between perfect code in the wrong architecture and code that actually fits.
RFCs are static documents. Prompts are interactive conversations. When you combine the discipline of one with the flexibility of the other, that's where the magic happens.
Without clear acceptance criteria, the agent doesn't know when to stop. The result is gold-plating or incomplete delivery - the same problems humans have, amplified.
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.