• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Deep Agents ships with built-in context management

    LangChain says filesystems, subagents and skills are already wired up to help manage what information an AI agent gets and when.

    LA
    SR
    2 Sources, ,

    TLDR

    LangChain calls context engineering—what information an agent gets and when—the biggest challenge for an agent harness. It says longer tasks make it harder to keep the context window from overloading, and presents Deep Agents’ built-in filesystems, subagents and skills as tools for managing that context.

    Combined views

    20.2K

    2 Sources, first seen 14d ago

    Combined views

    20.2K

    2 Sources, first seen 14d ago

    253 likes
    14d ago
    first seen 14d ago
    253 likes
    32 comments
    278 saves
    49 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    32 comments
    278 saves
    49 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    @LangChainThe biggest challenge facing an agent harness is context engineering, or what information an agent gets, and when. The longer the task, the harder it is to keep the context window from overloading. Deep Agents ships with this built in: filesystems, subagents, and skills, already wired up for context management.
    @sydneyrunklebuilding an agent (model + harness) is about 2 things: 1. picking the right model for the job. this means finding the sweet spot on the cost/intelligence curve. 2. building a harness that's fit to the agent's task(s). this means the harness can get the right context to the model at any step. here's a guide on how to build a domain specific harness: https://www.langchain.com/blog/how-to-build-a-custom-agent-harness

    2 Sources

    @LangChainThe biggest challenge facing an agent harness is context engineering, or what information an agent gets, and when. The longer the task, the harder it is to keep the context window from overloading. Deep Agents ships with this built in: filesystems, subagents, and skills, already wired up for context management.
    @sydneyrunklebuilding an agent (model + harness) is about 2 things: 1. picking the right model for the job. this means finding the sweet spot on the cost/intelligence curve. 2. building a harness that's fit to the agent's task(s). this means the harness can get the right context to the model at any step. here's a guide on how to build a domain specific harness: https://www.langchain.com/blog/how-to-build-a-custom-agent-harness