OpenAI's Kepler Agent Processes 580PB Daily, Cuts Query Time to 90s
Al_Grigor · x · 2026-08-26
OpenAI's Data Productivity team published a case study on Kepler, an internal AI data agent built on OpenMetadata serving 3,500+ employees. It enables self-service analytics across 70,000 datasets.
Key Results:
- Reduces data retrieval time from days to under 90 seconds.
- Processes 580+ PB daily with 15x faster queries.
- Every answer shows reasoning and enforces strict permissions.
Technical Implementation:
- Grounds answers in governed metadata (schemas, lineage, query history) for accuracy.
- Uses a six-layer context model and compounding memory.
- Enforces permissions at every layer, from retrieval to chain-of-thought.
More from coding & agent
- Open Source AI Skill /fuck-cancer Helps Patients Navigate Diagnosis — petergyang · 2026-08-26
- Muse Spark Beats DeepSeek 41 to 39 in Full-Stack Coding Showdown — marvijo-software · 2026-08-26
- Skepticism Around LLM-as-a-Judge: Biases and Overfitting Risks — Innowise_ · 2026-08-26
- MIT Prof Builds City Bots with Grok: AI Agents Co-Create SimCity — ProfBuehlerMIT · 2026-08-26
- Infinity App update: Multi-agent collaboration and process isolation — jasonkneen · 2026-08-26
- Shopify CEO threatens to ban Claude Code over fragmented config files — 机器之心 · 2026-08-26