LangChain's Managed Deep Agents ships with built-in web search from Parallel

LangChain has released Managed Deep Agents v0.8 in public beta, adding built-in Parallel Web Search to its fully managed LangSmith service for developing, deploying, and operating production AI agents. Developers can configure the search capability once in Python or TypeScript without separate vendor accounts, API keys, or custom search-tool integration, while LangSmith manages credentials and records search calls, latency, and errors in agent traces. Managed Deep Agents provides infrastructure including durable execution, memory, authentication, sandboxes, tool servers, observability, channels, and evaluations, allowing teams to focus on domain logic, prompts, and testing. The update also introduces identity-aware tool connections, personalized user-level memory, and Slack file transfer. Parallel Search returns ranked URLs and compressed, query-relevant excerpts from its web index, supporting agent context and source citation, and operates with zero data retention and no cost during the public beta.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.