<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Alban Capitant on Fred</title><link>https://site.fredlab.dev/contributors/alban-capitant/</link><description>Recent content in Alban Capitant on Fred</description><generator>Hugo</generator><language>en</language><copyright>Copyright (c) 2020-2024 Thulite</copyright><lastBuildDate>Sun, 17 Aug 2025 10:00:00 +0200</lastBuildDate><atom:link href="https://site.fredlab.dev/contributors/alban-capitant/index.xml" rel="self" type="application/rss+xml"/><item><title>MCP vs REST for RAG in Fred: Why We Run Both</title><link>https://site.fredlab.dev/blog/mcp-vs-rest-for-rag-in-fred-why-we-run-both/</link><pubDate>Sun, 17 Aug 2025 10:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/mcp-vs-rest-for-rag-in-fred-why-we-run-both/</guid><description>Fred uses REST for graph-driven RAG (Rico, Rico Pro) and MCP for tool-driven RAG (Dominic). Running both lets us measure latency, reliability, governance, and developer ergonomics—without changing our UI or schemas.</description></item><item><title> Ingest Smarter, Not Harder — Fred Gets a Temporal Brain</title><link>https://site.fredlab.dev/blog/ingest-smarter-not-harder-fred-gets-a-temporal-brain/</link><pubDate>Sun, 20 Jul 2025 19:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/ingest-smarter-not-harder-fred-gets-a-temporal-brain/</guid><description>Thanks to Temporal, Fred makes document ingestion as reliable as microservices — with automatic retries, fine-grained observability, and custom pipelines for push or pull ingestion. A true game-changer for AI apps.</description></item><item><title>Expanding Fred with MCP: A Playground for Next-Gen Agentic Architectures</title><link>https://site.fredlab.dev/blog/expanding-fred-with-mcp-a-playground-for-next-gen-agentic-architectures/</link><pubDate>Mon, 19 May 2025 12:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/expanding-fred-with-mcp-a-playground-for-next-gen-agentic-architectures/</guid><description>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.</description></item></channel></rss>