How Box built enterprise content agents on Deep Agents with a parent/child architecture
LangChain · x · 2026-10-28
A LangChain case study details how Box AI built its enterprise Box Agent on Deep Agents: simple requests are handled directly by the parent node without planning, while complex ones spawn child agents that distribute work behind a uniform invocation surface. The agent searches across content for 100,000+ enterprises and synthesizes thousands of documents while respecting Box's permissions model. Selection criteria were full model agnosticism and speed; the architecture evolved from single-file Q&A to RAG-based Knowledge Hubs to agents as users demanded cross-domain analysis like research synthesis and contract risk reviews.
Related event: Box Reveals Deep Agent Architecture with Dynamic Parent-Child Agents(2 posts)→
More from coding & agent
- Sequoia, Citi and OpenAI launch No Limit: build a poker bot in 60 minutes, $100K grand prize — polynoamial · 2026-10-28
- Judgment Labs launches publicly: monitoring and eval layer for long-horizon agents — testingcatalog · 2026-10-28
- OSU NLP Group Wins Three Paper Awards Same Day at EMNLP 2026 and NeurIPS Workshop — hhsun1 · 2026-10-28
- Replit launches Cloud Agents: non-engineers ship reviewed PRs from natural language — Jeff_Burke14 · 2026-10-28
- Sequoia and OpenAI host $100K poker bot tournament where agents build bots in 60 minutes — polynoamial · 2026-10-28
- PPCC26 demos praised: real orgs like NFL, real code live in VS Code, no fake companies — donasarkar · 2026-10-28