Presentation: AI Agents to Make Sense of Data at OpenAI
Quick Answer
OpenAI's Bonnie Xu presents Kepler, an AI data analyst agent that queries over 600 petabytes of data.
Quick Take
OpenAI's Bonnie Xu presents Kepler, an AI data analyst agent that queries over 600 petabytes of data. The team employs to address context window limits, automated code crawling, and for enhanced data analysis. They also utilize scoped semantic memory for self-learning and AST-based LLM grading for a robust evaluation pipeline.
Key Points
- Kepler is designed to analyze over 600 petabytes of data efficiently.
- MCP helps overcome context window limitations in data querying.
- Automated code crawling and RAG are utilized for improved data analysis.
- Scoped semantic memory enables self-learning capabilities in the agent.
- AST-based LLM grading ensures a regression-free evaluation pipeline.
Article Excerpt
From source RSS / original summaryOpenAI’s Bonnie Xu discusses Kepler, an internal AI data analyst agent built to query 600+ petabytes of data. She explains how they overcome context window limits using , automated code crawling, and . Xu also shares how their team leverages scoped semantic memory for self-learning and utilizes AST-based LLM grading to build a robust, regression-free evaluation pipeline. By Bonnie Xu
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from InfoQ AI, ML & Data Engineering
See more →
Windows Platform Security and the Race to Secure AI Agents
Microsoft's new Windows Developer Blog emphasizes Windows as the secure OS for AI agents, introducing the Microsoft Execution Containers (MXC) SDK to enhance containment, identity, and manageability within the operating system.
