<?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/</link><description>Recent content 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/index.xml" rel="self" type="application/rss+xml"/><item><title>Release Lifecycle</title><link>https://site.fredlab.dev/releases/lifecycle/</link><pubDate>Sat, 02 May 2026 00:00:00 +0200</pubDate><guid>https://site.fredlab.dev/releases/lifecycle/</guid><description>One production version at a time. Two branches. Hotfixes from main. This page makes the model explicit for contributors, operators, and the core team.</description></item><item><title>Roadmap</title><link>https://site.fredlab.dev/releases/roadmap/</link><pubDate>Sat, 02 May 2026 00:00:00 +0200</pubDate><guid>https://site.fredlab.dev/releases/roadmap/</guid><description>Swift golive on 31 July 2026, Swift 2.0 GA on 30 September 2026, and the milestones in between.</description></item><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>AI as an Engineering Partner — and How We Stay in Control</title><link>https://site.fredlab.dev/blog/ai-as-an-engineering-partner-and-how-we-stay-in-control/</link><pubDate>Wed, 08 Jul 2026 00:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/ai-as-an-engineering-partner-and-how-we-stay-in-control/</guid><description>Fred is a full cloud-native agentic platform: speed and batch layers, Temporal workflows, identity propagation, ReBAC authorization, observability. We use AI assistants — for code, but also for backlogs, RFCs, and PMO tracking. This post is an honest account of the guardrails we built into the repository so that the humans, not the assistants, stay in control of a robust, industrial, maintainable application.</description></item><item><title>Ingestion Shouldn't Be a Choice</title><link>https://site.fredlab.dev/blog/ingestion-shouldnt-be-a-choice/</link><pubDate>Wed, 10 Jun 2026 12:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/ingestion-shouldnt-be-a-choice/</guid><description>A look at why three ingestion modes create more problems than they solve, how the PDF extraction pipeline was rebuilt to be ten times faster with 90% fewer LLM calls, and the unified ingestion architecture that points toward removing the choice entirely.</description></item><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>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>Observability by Design in Fred: Prometheus, OpenSearch, and Spot</title><link>https://site.fredlab.dev/blog/observability-by-design-in-fred-prometheus-opensearch-and-spot/</link><pubDate>Fri, 03 Apr 2026 12:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/observability-by-design-in-fred-prometheus-opensearch-and-spot/</guid><description>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.</description></item><item><title>Beyond Agent Framework Wars: Fred and the Infrastructure Layer</title><link>https://site.fredlab.dev/blog/beyond-agent-framework-wars-fred-and-the-infrastructure-layer/</link><pubDate>Sat, 21 Feb 2026 10:00:00 +0200</pubDate><guid>https://site.fredlab.dev/blog/beyond-agent-framework-wars-fred-and-the-infrastructure-layer/</guid><description>Fred does not compete in the agent framework wars; it focuses on the production infrastructure layer for governed agent execution.</description></item></channel></rss>