Dimitri Tombroff

Ingest Smarter, Not Harder — Fred Gets a Temporal Brain

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.

July 20, 2025 in architecture, ops, orchestration by Alban Capitant, Simon Cariou, Florian Muller and Dimitri Tombroff5 minutes

Bridging the Dev DevOps Gap with AI Deployment Review

Instead of relying on fragile regex scripts or complex linters, Fred uses AI to catch mismatches between backend code and Helm deployments. This makes deployment safer and helps teams move faster.

July 14, 2025 in devops, configuration-management, ai-review by Dimitri Tombroff4 minutes

Using AI to Enforce Code Quality in Fred

We use GPT-4 internally to automate Python code reviews and ensure compliance with Fred's backend development standards. Learn how our AI review tool works and why it matters.

June 20, 2025 in devops, configuration-management, ai-review by Dimitri Tombroff5 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

Playing with Ollama

Running Fred with a local Ollama server

March 7, 2025 in guidance by Emanuel-Todor Hascau-Dumitrelea and Dimitri Tombroff2 minutes

EEvaluating LLM Applications in the Enterprise: A Major Challenge

Large Language Models (LLMs) are revolutionizing enterprise automation and decision-making, but evaluating their effectiveness with proprietary data poses unique challenges. This post explores these complexities and their critical importance for successful enterprise adoption.

January 12, 2025 in architecture by Tanguy Jouannic, Dimitri Tombroff and Dorian Finel-Bacha16 minutes

Fred design and architecture

A state-of-the-art and effective multi-agent Kubernetes assistant

October 3, 2024 in architecture by Tanguy Jouannic, Dimitri Tombroff, Lorenzo Gerardi and Reyyan Tekin24 minutes