Snowflake Adds Governance Controls for Enterprise AI Agents
Snowflake introduced controls for identifying agents, capping their permissions, masking sensitive values, limiting AI credit consumption, and auditing their activity, according to InfoQ 中文 AI&大模型. Its agent-restricted session scopes and per-user AI credit quotas are generally available, while CoCo automation remains in public preview and runs unattended in a Snowflake-managed sandbox. The report notes that audit views can only reveal activity by agents Snowflake has recognized and recorded.
The controls provide enterprises with a combined framework for governing agent identity, access, data exposure, resource usage, and accountability as agents act on users’ behalf.
2026 年，智能体将在企业级应用中取得哪些实质性突破？点击下载"《2026 年 AI 与数据发展预测》白皮书，获悉专家一手前瞻，抢先拥抱新的工作方式！
AI 智能体不只是回答问题。它们还会查询数据、调用工具，并替你执行操作。问题在于，智能体代表你行动时，也可能继承你的访问权限。这带来了治理挑战：如何在赋予智能体完成任务所需权限的同时，避免授予超出需要的权限？
人可以查看敏感数据，并自行判断如何处理。智能体则可能通过汇总敏感数据、将其传递给其他工具，或把数据呈现给无权访问的人，大规模暴露敏感信息。
Snowflake 提供了五项控制措施来管理这类行为：识别智能体、限制其权限、保护敏感数据、控制资源消耗，并审计其行为。
#Snowflake#Cortex Agents#Cortex Lite Agents#CoCo#CoWork#AI Functions#Snowflake-managed MCP servers