Box Agent Adopts LangChain Deep Agents for Secure Enterprise Analysis

LangChain

Jun 15, 2026

Box Agent now uses LangChain's Deep Agents framework to search, synthesize, and analyze enterprise content. The architecture employs a parent-child agent model to handle complex tasks like multi-document synthesis and structured report generation. It operates within Box's existing security and permissions model, ensuring agents only access content authorized for the specific user.

Box Agent Architecture; AI Studio; Agent Configurations; Agent Orchestrator (LangGraph Service); Global Agent; SubAgent; SubAgent; Tools; Middleware; Guardrails; AI Center AX; AI APIs; Box MCP; Intelligence Service; LLM Gateway; Providers — Box Agent architecture diagram illustrating the integration of LangGraph services for orchestrating subagents, tools, and LLM providers.

View the full update on langchain.com

LangChain

@LangChain2d ago

.@Box Agent is built on Deep Agents. ✅ Cross-library search ✅ Multi-doc synthesis ✅ Structured reports ✅ All within Box's existing security and permissions model https://t.co/UFlJzFcCRe

2192

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

Keep reading

LangChain Simplifies Production AI Agent Deployment with Managed Deep Agents

LangChain introduced Managed Deep Agents in private beta, an API-first hosted runtime for its open-source Deep Agents. This offering aims to streamline the operational complexities of deploying autonomous AI agents, allowing developers to focus on agent behavior rather than managing infrastructure.

PerplexityYesterday

Perplexity Integrates Deep Research as a Native Skill in Computer

Perplexity integrated Deep Research as a native skill within its Computer agent platform. The system uses a Search as Code architecture to run thousands of parallel retrieval steps, allowing it to synthesize reports, decks, and dashboards from primary sources and user files. This update is available now to all Pro and Max subscribers.

Google Research Boosts RAG Accuracy with Iterative Agentic Context Search

GoogleJun 7

Google Research Boosts RAG Accuracy with Iterative Agentic Context Search

Google Research and Google Cloud introduced a new agentic RAG framework designed to handle complex enterprise queries. This framework employs a multi-agent workflow that iteratively searches for sufficient context, improving accuracy beyond standard Retrieval-Augmented Generation (RAG). It aims to deliver more dependable responses by preventing the AI from guessing when information is incomplete across multiple data sources.

OpenAI Updates Agents SDK to Support Secure Sandboxes and Durable Execution

OpenAIApr 15

OpenAI Updates Agents SDK to Support Secure Sandboxes and Durable Execution

OpenAI updated its Agents SDK with a model-native harness and native sandbox execution to help developers build production-grade autonomous agents. By separating the agent's logic from its execution environment, the system enables durable runs that can recover from crashes and execute code safely in isolated workspaces.