Most integration estates do not fail because someone picked the wrong queue product. They fail because every project rebuilds the same verbs—file drop, route, transform, deliver—with slightly different code, different secrets handling, and no shared ops…
The first support ticket after a RAG go-live rarely says “the embedding model is wrong.” It says the bot invented a policy clause, cited a retired PDF, or missed the answer that sat two paragraphs below…
A pilot demo once looked flawless on stage and collapsed the week after: the model answered well, the tools were real, and nobody could say which system owned identity, data egress, or the kill switch. The…
Security review killed a pilot I was proud of for one boring reason: the model path could reach a write API with a service identity that was “temporary.” Temporary lasted six weeks. The demo still worked.…
A bank delivery lead once asked me, mid-sprint review: “Who owns the AI bit when it hits production?” Three vendors, two platform teams, and a shiny pilot later, nobody could name a single owner for identity,…
A staging agent once “fixed” a support ticket by refunding the wrong order. The reply sounded confident. The tool call succeeded. The business outcome was still wrong. That is why I care less about demo wow-factor…
Every few months the industry invents a new label for “multiple model calls that somehow cooperate,” and right now one of the loudest is dynamic workflow — especially inside Claude Code. In this post I unpack…
Once you have more than one MCP server, the question stops being “how do I expose a tool?” and becomes “how do I expose many tools without turning every AI client into a spaghetti of credentials,…