AI-Powered Automation & Incident Response Consulting
I build AI-assisted tooling that shortens incidents and removes manual operations, always with guardrails around anything that can change production.
What I help with
- RAG pipelines that make internal documentation searchable
- Slack bots that investigate incidents using documentation search, metric plugins and log APIs
- Automated incident root cause analysis and response
- Fleet automation with host draining and safety guardrails
- AI-assisted development of internal tools and TUIs using Claude Code, Roo Code and Gemini
- Spec-driven, agentic engineering workflows
Relevant experience
- Built AI-powered RAG pipelines to automate documentation search
- Created a Slack bot that automatically investigates incidents
- Automated incident root cause analysis and incident response
- Automated upgrades for a fleet of 2000+ machines with proper host draining and guardrails
- Leverage AI-assisted coding to build interactive TUIs and automation tooling quickly
Related articles
Incident Management: Post-Mortem Culture That Works
The world of complex distributed systems is inherently unpredictable. Despite our best efforts in design, testing, and deployment, incidents are not a question of “if,” but “when.” For Site Reliability Engineers, Softwar
Observability vs Monitoring: Understanding the Difference
In the rapidly evolving landscape of distributed systems, microservices, and cloud-native architectures, the terms “observability” and “monitoring” are often used interchangeably, leading to confusion and, more criticall