RootCauseAI

The Problem We Wanted to Solve

When a production incident hits, L1/L2 support engineers waste hours jumping between systems. They check Jira for history, dig through git commits, query databases, read documentation, all manually. By the time they find the root cause, hours have passed.

Cloud-based AI tools could help, but many organisations (especially in regulated industries) can't send their code, logs, and database schemas to external APIs. They need something that runs entirely on-premise.

What We Built

RootCauseAI is a self-hosted investigation engine that:

• Runs locally using Ollama - No data leaves your infrastructure
• Connects to your existing tools - Jira, Redmine, Git, SQL databases, MongoDB
• Uses RAG for context - Indexes your documentation and past incidents
• Analyses code - Reviews relevant code paths for the failing component
• Suggests root causes - Based on patterns from similar past incidents

Technical Architecture

The main design decision was making it work entirely on-premise. Most of the mining and resources businesses our team has worked with can't send production data to cloud APIs. RootCauseAI runs as a Docker container using Ollama for inference, with connectors to common enterprise tools.

Languages supported: PHP, Java, C#, ASP.Net, Angular: the "boring" enterprise stack that most real businesses actually run.

What We Learned

Building RootCauseAI showed us that on-premise AI runs on ordinary hardware. With quantised models on Ollama, you can get useful AI assistance on a standard server without a GPU cluster. That has changed how we advise clients about data sovereignty options.