# Perplexity details CobbleDB database built with AI coding agents

CobbleDB replaced DynamoDB, cutting median batch-read latency from 31.4 ms to 5.60 ms and p99 latency from 123 ms to 24.2 ms.

- Two engineers and hundreds of proactive AI agents built the core infrastructure in two months.
- The system partitions page keys and reads them in parallel using RocksDB MultiGet while querying alternate replicas if a response lags.
- Document state is separated across Pillar for storage in YTsaurus, Lorry for S3 update batches, and CobbleDB for serving.
- Perplexity estimates at least 20% cost savings compared to DynamoDB.
- Perplexity plans to open-source CobbleDB for teams building AI search applications.

## Why it matters

Developers building AI retrieval systems have a reference architecture showing how tailored storage engines and autonomous coding agents can cut database latency and cloud costs.

## Sources

- [Perplexity: Perplexity details CobbleDB database built with AI coding agents](https://x.com/perplexity_ai/status/2099955628194316346)

---

Summarized by dstilled on 2026-09-15. https://dstilled.ai/story/b48b28f5-68a7-45a9-82e1-69bd44e516b6