I built a multiverse for AI agents: they rehearse every action in hundreds of graph copies before touching anything

说明与用途

Multiverse 让 AI 代理在数百个图复制中排练每个操作，评估关键失败的概率并阻止不安全的计划。

问题

AI agents perform actions on real systems, but silent dependencies can cause critical failures when an action is taken.

结果

Multiverse blocks unsafe actions when the probability of breaking a critical component exceeds 5%, reducing risk of silent failures.

工作流

• Snapshot the company graph with GRAPH.COPY
• Create a fresh copy for each simulated future
• Roll dice for every uncertain link to decide if it exists in that future
• Apply the planned change in the copy
• Run a ripple query to detect failures and record what broke
• Delete the copy

证据

AI agents are starting to act on real systems. They clean up databases, rotate keys, move cron jobs, scale services. The action itself is rarely the dangerous part. The danger is everything that silently depends on the thing being changed.

来源

Multiverse treats the company as a graph in FalkorDB, and every uncertain link as a coin with a known bias.

来源

Each future becomes one square on screen. Orange means something business-critical broke. After enough futures, Multiverse knows the chance of breaking something critical, and if it's 5% or more, the plan is blocked.

来源