AI Coding Live News

Perplexity used hundreds of AI coding agents to build CobbleDB for its search stack

Perplexity says two engineers worked with hundreds of AI coding agents to build CobbleDB, a custom Rust database replacing DynamoDB reads in its search stack. The case shows coding agents contributing at real infrastructure scale while keeping production execution outside the agents’ permissions.

Key Takeaways

  • Two engineers coordinated hundreds of AI coding agents to build the custom Rust CobbleDB database
  • CobbleDB replaces DynamoDB read paths in Perplexity’s search stack
  • Agents built the system but were not allowed to run the database, separating coding from production authority
Read full story
Linked Models & Agents:

Perplexity: two engineers + hundreds of AI agents built CobbleDB in two months, ~5× lower latency vs DynamoDB

Perplexity (@perplexity_ai) published CobbleDB: a key-value store built in two months by two engineers and hundreds of proactive always-on AI agents for Perplexity search web-content serving. After replacing DynamoDB, median batch-read latency fell from 31.4 ms to 5.60 ms and p99 from 123 ms to 24.2 ms; they plan to open-source it for other AI search teams.

Key Takeaways

  • Two engineers plus hundreds of AI agents built production CobbleDB in two months.
  • Vs DynamoDB, median/p99 batch-read latency dropped ~5× (31.4→5.6 ms, 123→24.2 ms).
  • Perplexity plans to open-source CobbleDB for other AI search teams.
Read full story
Linked Models & Agents: