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

    Perplexity publishes research on CobbleDB, its in-house search database

    Perplexity says two engineers and hundreds of always-on AI agents built CobbleDB’s core infrastructure in two months.

    AS
    PE
    2 Sources, ,

    TLDR

    Perplexity is publishing research on how it built CobbleDB, a key-value database it says serves web content for Perplexity search. The company credits two engineers and hundreds of proactive, always-on AI agents with building the core infrastructure in two months. Aravind Srinivas describes CobbleDB as a replacement for AWS DynamoDB and projects savings of up to $100 million a year from migrating to it.

    Combined views

    877K

    2 Sources, first seen 15d ago

    Combined views

    877K

    2 Sources, first seen 15d ago

    4.1K likes
    15d ago
    first seen 15d ago
    4.1K likes
    236 comments
    1.5K saves
    291 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    236 comments
    1.5K saves
    291 reposts
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    2 Sources

    @perplexity_aiWe’re publishing research on how we built CobbleDB, our key-value database that serves web content for Perplexity search. Two engineers and a team of hundreds of proactive, always-on AI agents built the core infrastructure in two months.
    @AravSrinivasWe built a replacement for AWS DynamoDB, a key-value database for fast web content fetches. This was done with two engineers and hundreds of persistent Computer agents over two months. Migrating to our in-house database will save us up to a hundred million dollars yearly.

    2 Sources

    @perplexity_aiWe’re publishing research on how we built CobbleDB, our key-value database that serves web content for Perplexity search. Two engineers and a team of hundreds of proactive, always-on AI agents built the core infrastructure in two months.
    @AravSrinivasWe built a replacement for AWS DynamoDB, a key-value database for fast web content fetches. This was done with two engineers and hundreds of persistent Computer agents over two months. Migrating to our in-house database will save us up to a hundred million dollars yearly.