<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Fred</title><link>https://site.fredlab.dev/tags/fred/</link><description>Recent content on Fred</description><generator>Hugo</generator><language>en</language><copyright>Copyright (c) 2020-2024 Thulite</copyright><lastBuildDate>Thu, 16 Apr 2026 12:00:00 +0200</lastBuildDate><atom:link href="https://site.fredlab.dev/tags/fred/index.xml" rel="self" type="application/rss+xml"/><item><title>Tabular Data in Fred: ReBAC-Scoped Parquet, S3, and DuckDB</title><link>https://site.fredlab.dev/blog/tabular-data-in-fred-rebac-scoped-parquet-s3-and-duckdb/</link><pubDate>Thu, 16 Apr 2026 12:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/tabular-data-in-fred-rebac-scoped-parquet-s3-and-duckdb/</guid><description>Fred now treats tabular data like the rest of the corpus: document-scoped, team-aware, and authorization-first. This post explains why the old SQL-store model was limiting, how the new Parquet plus DuckDB runtime works, and what this changes for security, performance, and operations.</description></item><item><title>From SQL to Agent: Smart Database Access in Fred</title><link>https://site.fredlab.dev/blog/from-sql-to-agent-smart-database-access-in-fred/</link><pubDate>Wed, 20 Aug 2025 10:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/from-sql-to-agent-smart-database-access-in-fred/</guid><description>What started with CSV ingestion has grown into full SQL integration. With Fred’s new SQLTableStore, you can query, update, and enrich your databases naturally through agents like Tessa.</description></item><item><title>Brontë: A New Content Generator Agent in Fred</title><link>https://site.fredlab.dev/blog/bront%C3%AB-a-new-content-generator-agent-in-fred/</link><pubDate>Mon, 18 Aug 2025 10:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/bront%C3%AB-a-new-content-generator-agent-in-fred/</guid><description>Instead of relying on traditional form-based UIs, Brontë guides users step by step in designing complex templates and prompts, ensuring correct formats and properties, and saving them directly to Fred’s knowledge base using MCP.</description></item><item><title>Rico Learns to Reflect: Smarter Document Q&amp;A with Self-RAG Techniques</title><link>https://site.fredlab.dev/blog/rico-learns-to-reflect-smarter-document-qa-with-self-rag-techniques/</link><pubDate>Tue, 05 Aug 2025 17:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/rico-learns-to-reflect-smarter-document-qa-with-self-rag-techniques/</guid><description>Rico, the document expert agent in Fred, now leverages Self-RAG-inspired strategies to assess document quality, retry with smarter queries, and generate more accurate answers. This post explains the improvements.</description></item><item><title>Power-Aware Kubernetes with MCP and Kepler</title><link>https://site.fredlab.dev/blog/power-aware-kubernetes-with-mcp-and-kepler/</link><pubDate>Mon, 02 Jun 2025 16:30:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/power-aware-kubernetes-with-mcp-and-kepler/</guid><description>Fred can now observe power and energy usage in Kubernetes via MCP and Kepler. This post walks through the setup and shows example visualizations and insights.</description></item><item><title>Introducing the New Fred Architecture: Modular, Agentic, and Knowledge-Aware</title><link>https://site.fredlab.dev/blog/introducing-the-new-fred-architecture-modular-agentic-and-knowledge-aware/</link><pubDate>Wed, 07 May 2025 16:27:22 +0200</pubDate><guid>https://site.fredlab.dev/blog/introducing-the-new-fred-architecture-modular-agentic-and-knowledge-aware/</guid><description>Fred is now composed of three modular components: a React UI, an agentic backend using LangGraph, and a knowledge-centric backend for document processing. Learn how it all fits together.</description></item></channel></rss>