Practical use of AI/LLM

Using an agent to build an agent (Without building Skynet)

René Nijkamp

René Nijkamp

René is a Product Architect at Backbase, where he builds the integration platform connecting banks to their core systems. Currently automating customer onboarding with AI agents, while fighting fires and enabling customer rollouts. He's been connecting systems that weren't designed to talk to each other for about 20 years. Prefers his fires on the BBQ.

Banking customer onboarding used to mean spreadsheets, Slack threads, and copy-pasting Kubernetes and APIM configs between teams and Github repos. My director sketched out an idea to streamline it. I picked it up and built an AI agent to orchestrate the delivery. Using another AI agent.

One agent writing another that touches real banking infrastructure. What could possibly go wrong?

Quite a lot. I'll cover the safety patterns that keep a recursive trust chain under control, the multi-persona approach that replaced the team I don't have, and the production scars that taught me why idempotency matters more than intelligence.

No frameworks pitch. No 30-minute demo. Real code, real banks, real consequences.