Acceptance Criteria: When the Agent Knows It's Done
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.
Read article
Introduction
Software engineer,
builder, and
Elixir enthusiast.
Recent Articles
Interfaces and Contracts: How Agents Respect Boundaries
Without explicit contracts, each agent invents its own interface. The result? Systems that work alone but break together.
Read article
Explicit Constraints: The Power of 'Don't Do This'
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.
Read article
The Anatomy of a Good System Prompt
Every section of an RFC has an exact mirror in the world of prompts. Once you see the mapping, writing prompts becomes second nature.
Read article
The Anatomy of a Good RFC
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.
Read article
Work
-
- Company
- EasyMate AI
- Role
- Software Engineer
- Date
-
- Company
- Iago Cavalcante Consultoria
- Role
- Software Engineer
- Date
-
- Company
- Zarv Inc.
- Role
- Software Engineer
- Date
-
- Company
- Truelogic
- Role
- Software Engineer
- Date
-
- Company
- IdopterLabs
- Role
- Software Engineer
- Date