Original post · AI translation
眼下，许多实用的智能体基础设施正在模型之下的数据层构建。
智能体整天查询相同的表，而每次请求都需要最新的行以及完整的历史数据。
@Eon_io_ 为这种模式构建了 Eon Yukon。它将事件摄取、清洗并压缩到存放在你自己的存储桶中的开放 Iceberg 表里，智能体则通过 MCP 读取每张表的上下文。 在 Eon 的公开基准测试中，它使用的计算资源比 Spark 少 4 倍，比 Flink 少 7 倍。
这在预料之中，因为智能体如果在查询表之前就知道表中有什么，就能避免大量无谓的扫描。
我目前在整个行业看到的是，AI 应用的最大瓶颈并非模型能力，而是数据基础设施。
今天，我们推出 Eon Yukon，进一步扩展 Eon Data Foundation。这是一款专为改变这一现状而打造的新型无服务器数据引擎。
AI 智能体需要新鲜且有上下文的数据才能采取行动。
专用模型需要持续获得数据和反馈才能改进。但两者仍由为仪表板打造的技术栈、架构和方法提供支持：
-按峰值负载配置的 Spark 和 Flink 集群，以及维持表可用性的压缩作业。
-为每个数据使用方分别建立一条管道和一份副本，按铜层、银层、金层分阶段处理。
-由人工编写、通过编排器连接并由专业人员维持运行的作业。
结果是：交付数据复杂、风险高且成本昂贵。虽然编程智能体能在几小时内交付应用，但它们很少构建或运行数据管道。数据变化太快，出错的代价也太高。
借助 Yukon，数据在单一连续流程中从摄取进入处理，再进入数据服务，无需传统上用来连接这些环节的基础设施和管道。
事件会在数秒内变成经过压缩、排序和去重的 Iceberg 表。
实时聚合在流程中直接运行，状态得到全面托管。智能体和应用可以通过兼容 Redis 的 API，或通过我们兼容 SQL 和 Spark 的查询引擎，以低于 1 毫秒的延迟访问新鲜数据。
除了传输和提供数据服务，Yukon 还让数据持续保持可理解：可通过 MCP 访问的实时列级统计信息，让智能体了解数据。内置的监控、采样和数据最小化功能帮助团队保持控制。
在每秒 100 万个事件且数据新鲜度相同的条件下，Yukon 使用的计算资源比 Spark 少 4 倍，比 Flink 少 7 倍。该基准测试已公开：你可以使用 Eon 的 ingest-bench 自行运行。
这是朝着我们为 AI 时代打造自主数据基础的愿景迈出的又一重要一步，旨在保护企业数据，同时释放其全部潜力。
Original
What I'm seeing across the industry right now is that the biggest bottleneck to AI adoption isn't model capabilities. It's data infrastructure. Today, we're expanding the Eon Data Foundation with the launch of Eon Yukon, a new serverless data engine purposely built to change that. AI agents need fresh, contextualized data to act. Specialized models need a continuous feed of data and feedback to improve. Both are still served by a stack, an architecture, and methods built for dashboards: -Spark and Flink clusters sized for peak, plus compaction jobs to keep tables usable. -A pipeline and a copy for every consumer, staged bronze to silver to gold. -Hand-written jobs, wired together by an orchestrator and kept alive by specialists. The result: shipping data is complicated, risky, and expensive. While coding agents ship apps in hours, they rarely build or run data pipelines. The data is too volatile, and a mistake costs too much. With Yukon, data moves from ingestion to processing to serving in one continuous flow, without the infrastructure and pipelines traditionally required to connect them. Events become compacted, sorted, deduplicated Iceberg tables within seconds. Real-time aggregations run inline, with fully managed state. Agents and applications can access fresh data with sub-millisecond latency through a Redis-compatible API or through our SQL and spark compatible query engine. Beyond moving and serving data, Yukon makes it continuously understandable - Live column-level statistics, accessible through MCP, give agents visibility into the data. Built-in monitoring, sampling, and data minimization help teams maintain control. At 1M events/sec and equal freshness, Yukon used 4x less compute than Spark and 7x less than Flink. The benchmark is public: run it yourself with Eon’s ingest-bench. This is another major step toward our vision of an Autonomous Data Foundation for the AI era, built to both protect enterprise data and unlock its full potential.