Original Summary

Hi HN!<p>I am an FDE and in all my clients&#x27; projects I have encountered the same problem: real world data preparation is the bottleneck. Company data doesn&#x27;t only come with the usual Kaggle problems, it also has a wide range of other problems: corrupted migrations, multiple versions of taxonomies, duplicate columns and many more. Each problem requires a decision and portia helps accelerate all those and keep everything in a long term memory making work sessions persist from one chat to another. Today portia works with Claude Code, Codex or a local model (llama.cpp or ollama). The data can be a Postgres database, CSV files or hosted in the cloud (Snowflake or BQ).<p>Happy to answer any questions!

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/10/7 23:00:45