One Truth. Many Agents. Zero Drift.
One agent is a tool. Many agents without shared identity is chaos. The multi-agent era needs a single source of truth about what the software is.
Thinking on software identity, agentic development, and the engineering decisions that persist.
One agent is a tool. Many agents without shared identity is chaos. The multi-agent era needs a single source of truth about what the software is.
Specs drift because they describe states. Deltas survive because they describe decisions. Stop writing better documents. Start declaring better deltas.
When AI makes execution cheap, the scarce resource is not typing. It is deciding. The discipline of the next era is knowing the difference.
Beck, Karpathy, and Willison arrived at the same conclusion independently: AI agents need persistent, structured specifications. The vocabulary differs. The diagnosis doesn't.
Context changes per request. Identity persists across sessions, tools, and team members. Context engineering without identity engineering is a database query without a schema.
Platform teams are the natural governance layer for AI agents. Here's the framework for making it work.
MCP has 97 million monthly SDK downloads and no built-in identity layer. That's a problem.
Your AI agents have credentials, make API calls, and access production data. They're operating on borrowed human identities with no scoped permissions. That's an identity crisis.
More context isn't the answer. The right context is. Your agent needs a schema to query, not a haystack to search.
Twitter rewrote Ruby to Scala. Uber's microservices have a 1.5-year half-life. The code is always temporary. The question is what persists.
We use cookies to understand how you use ribo.dev and improve your experience.
Learn more in our Cookie Policy