{"type":"post","id":"how-we-optimized-browser-use-for-deep-agents-5d66fb","slug":"how-we-optimized-browser-use-for-deep-agents-5d66fb","title":"How We Optimized Browser Use for Deep Agents","description":"LangChain describes how it selected and optimized browser tools for Managed Deep Agents, reporting large differences in cost, speed and task success across tool designs.","retrieval_nugget":"LangChain describes how it selected and optimized browser tools for Managed Deep Agents, reporting large differences in cost, speed and task success across tool designs. For teams building browser agents, its results suggest that harness choices—especially batching actions and controlling returned context—can matter as much as model choice.","published_at":"2026-11-03","updated_at":"2026-11-03","record_date":"2026-11-03","date_kind":"published_at","topics":["claude","mcp"],"entities":["LangChain","Managed Deep Agents","Stagehand","Browserbase","Claude Sonnet 5.5","Claude Opus 5.5","LangSmith"],"related_patterns":["harness-architecture-outlives-model-choice"],"novelty_label":"new_fact","what_changed":"LangChain details how it optimized browser use for deep agents, including its iterative trace-and-evaluate process and the role of Stagehand tools.","prior_refs":["memory:645a37db-cbf5-8297-ac2c-2daf547d8fc5","memory:2f677b25-40e4-8bd6-ad95-0f74f962103c"],"source_url":"https://www.langchain.com/blog/how-we-optimized-browser-use-for-deep-agents","source_urls":["https://www.langchain.com/blog/how-we-optimized-browser-use-for-deep-agents"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:how-we-optimized-browser-use-for-deep-agents-5d66fb","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/how-we-optimized-browser-use-for-deep-agents-5d66fb/","markdown":"https://newruntime.com/posts/how-we-optimized-browser-use-for-deep-agents-5d66fb.md","json":"https://newruntime.com/posts/how-we-optimized-browser-use-for-deep-agents-5d66fb.json"},"next_reads":[{"type":"topic","path":"/topics/claude/","url":"https://newruntime.com/topics/claude/","title":"Claude","reason":"Explore the claude topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude.md","json_url":"https://newruntime.com/topics/claude.json"},{"type":"topic","path":"/topics/mcp/","url":"https://newruntime.com/topics/mcp/","title":"Mcp","reason":"Explore the mcp topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/mcp.md","json_url":"https://newruntime.com/topics/mcp.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}