According to monitoring by 1M AI News, the AI search engine Exa has launched the Monitors feature, allowing developers to set up timed search tasks. The search results are automatically deduplicated and pushed via Webhook, returning only new content since the last run. Exa's search API is utilized by companies such as Cursor, Notion, AWS, and Databricks, positioning itself as a search infrastructure for AI Agents. Monitors supports customizable search frequencies (as short as 1 hour) and allows specification of structured JSON output formats through the outputSchema parameter, such as automatically extracting fields like company names, funding rounds, and amounts, or opting for plain text summaries. In addition to timed triggers, it supports manual instant execution and provides three integration methods: Python, JavaScript, and cURL. Typical use cases include tracking competitor dynamics, monitoring funding announcements in specific fields, and following academic paper publications. Previously, AI Agents primarily relied on actively calling search APIs to obtain external information; Monitors shifts this model from on-demand queries to subscription-based pushes, enabling Agents to continuously receive incremental information without polling.