Title here
Summary here
Knowledge-Flow
Tabular Data in Fred: ReBAC-Scoped Parquet, S3, and DuckDB
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.
April 16, 2026 in SQL, architecture by Simon Cariou7 minutes
Observability by Design in Fred: Prometheus, OpenSearch, and Spot
Fred now treats observability as a first-class platform capability. With Spot, users can discover Prometheus and OpenSearch tools over MCP, ask monitoring questions in natural language, generate exact PromQL, and persist audit reports to MinIO-backed storage.
April 3, 2026 in observability, platform by Simon Cariou9 minutes
Rico Learns to Reflect: Smarter Document Q&A with Self-RAG Techniques
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.
August 5, 2025 in agents, update by Romain Perennes4 minutes
Expanding Fred with MCP: A Playground for Next-Gen Agentic Architectures
Fred is now capable of serving and consuming components over the Model Context Protocol (MCP). Discover how this unlocks new architectures and makes Fred a live testbed for building interoperable AI agents.
May 19, 2025 in architecture, mcp, open-source by Simon Cariou, Alban Capitant and Dimitri Tombroff6 minutes
Introducing the New Fred Architecture: Modular, Agentic, and Knowledge-Aware
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.
May 7, 2025 in architecture, announcement by Kevin Denis, Dorian Finel-Bacha, Julien Ornat, Fabien Le-Solliec and Dimitri Tombroff4 minutes