Title here
Summary here
Blog
Continuous Evaluation, Made Visible: fred-agent-evaluator in Action
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.
July 9, 2026 in agents, evaluation by Odelia Cohen, Dimitri Tombroff and Thomas Delavallade8 minutes
AI as an Engineering Partner — and How We Stay in Control
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.
July 8, 2026 in engineering, ai by Dimitri Tombroff, Simon Cariou and Yahya Zaim Mounajed8 minutes
Ingestion Shouldn't Be a Choice
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.
June 10, 2026 in architecture by Timothé Le Chatelier10 minutes
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
Rich Mode: Extending RAG with Direct Visual Evidence
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.
April 13, 2026 in agents, architecture by Odelia Cohen6 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
Beyond Agent Framework Wars: Fred and the Infrastructure Layer
Fred does not compete in the agent framework wars; it focuses on the production infrastructure layer for governed agent execution.
February 21, 2026 by Dimitri Tombroff13 minutes
Document Ingestion Is Not a Side Effect
Document ingestion is a first-class architectural concern in agentic platforms, and fast attachment is not the same as durable corpus ingestion.
February 14, 2026 by Fred Team7 minutes
Durable AI Agents: Orchestrating the Future with Fred and Temporal
Fred extends its existing agentic backend with a Temporal-powered execution path for long-running tasks. Workflows remain resilient through retries, heartbeats, and durable state, while agent contracts and tool boundaries stay explicit and portable.
February 4, 2026 in architecture, ai by Dimitri Tombroff and Simon Cariou6 minutes
Relationship-Based Access Control in Fred with OpenFGA
Fred’s backend now ships a ReBAC model powered by OpenFGA. Tags, documents, and resource libraries inherit permissions, groups are first-class, and every check flows through centralized authorization—bringing Drive-like sharing semantics to agentic workflows.
December 18, 2025 in security, platform by Florian Muller and Simon Cariou7 minutes