<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agents on Fred</title><link>https://site.fredlab.dev/categories/agents/</link><description>Recent content in Agents on Fred</description><generator>Hugo</generator><language>en</language><copyright>Copyright (c) 2020-2024 Thulite</copyright><lastBuildDate>Fri, 24 Jul 2026 08:00:00 +0200</lastBuildDate><atom:link href="https://site.fredlab.dev/categories/agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Excel, but Agent-Ready: How Fred Turns Spreadsheets into Queryable Knowledge</title><link>https://site.fredlab.dev/blog/excel-but-agent-ready-how-fred-turns-spreadsheets-into-queryable-knowledge/</link><pubDate>Fri, 24 Jul 2026 08:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/excel-but-agent-ready-how-fred-turns-spreadsheets-into-queryable-knowledge/</guid><description>Excel is not a document — it&amp;rsquo;s a data source wearing a document&amp;rsquo;s clothes. Here is how Fred rebuilds the structure of a workbook deterministically, hands the agent a global map plus queryable tables, and adds a server-side value locator that collapses a dozen blind queries into a single targeted one.</description></item><item><title>Continuous Evaluation, Made Visible: fred-agent-evaluator in Action</title><link>https://site.fredlab.dev/blog/continuous-evaluation-made-visible-fred-agent-evaluator-in-action/</link><pubDate>Thu, 09 Jul 2026 10:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/continuous-evaluation-made-visible-fred-agent-evaluator-in-action/</guid><description>The Admin of a Fred team is accountable for how its agents behave — but accountability without visibility is just exposure. fred-agent-evaluator is what gives that accountability something to stand on, including custom, business-specific checks an Analyst can define just by describing them.</description></item><item><title>Rich Mode: Extending RAG with Direct Visual Evidence</title><link>https://site.fredlab.dev/blog/rich-mode-extending-rag-with-direct-visual-evidence/</link><pubDate>Mon, 13 Apr 2026 12:07:05 +0100</pubDate><guid>https://site.fredlab.dev/blog/rich-mode-extending-rag-with-direct-visual-evidence/</guid><description>An exploration of the structural limitations of text-based RAG systems, supported by benchmarks, and how Rich mode introduces a multimodal retrieval strategy that preserves and leverages images as first-class evidence.</description></item><item><title>Comparing Graph-Centric and Reflective RAG Agents in Fred</title><link>https://site.fredlab.dev/blog/comparing-graph-centric-and-reflective-rag-agents-in-fred/</link><pubDate>Tue, 16 Dec 2025 12:07:05 +0100</pubDate><guid>https://site.fredlab.dev/blog/comparing-graph-centric-and-reflective-rag-agents-in-fred/</guid><description>A comparison of Fred’s graph-centric RAG agent (Richard) and reflective RAG agent (Rico), including architecture and evaluation metrics.</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>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>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>From CSV to Agent: Tabular Data Gets Smart in Fred</title><link>https://site.fredlab.dev/blog/from-csv-to-agent-tabular-data-gets-smart-in-fred/</link><pubDate>Fri, 11 Jul 2025 14:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/from-csv-to-agent-tabular-data-gets-smart-in-fred/</guid><description>Fred now supports agentic access to tabular data like CSV and Excel through a new DuckDB-based backend and the Tessa agent. Explore how this works and what it unlocks.</description></item></channel></rss>