By @indianexpress
Publication Date: 2026-01-04 08:51:00
Jaana Dogan, a principal engineer at Google who works on the Gemini API, recently shared a mind-boggling experience on testing Anthropic’s Claude Code, an AI-powered coding assistant. In a post on X, Dogan stated that she provided Claude Code with a problem description and, within one hour, received a result that closely matched what her Google team had been working on for the past year.
Dogan goes on to explain that the task involved distributed agent orchestrators, which are systems that coordinate multiple AI agents. Dogan added that Google had tried many approaches to this problem but had not reached a final design.
“I’m not joking and this isn’t funny. We have been trying to build distributed agent orchestrators at Google since last year. There are various options, not everyone is aligned… I gave Claude Code a description of the problem, it generated what we built last year in an hour,” Dogan wrote.
She explained that the prompt she gave Claude Code was not very…
