The Expert Who Never Retires: Tweezr on the IBM Z and LinuxONE Ecosystem Podcast
Ohad Kotler joins IBM's z/Action! series to talk about agentic root-cause analysis, tested fixes, and why AI transformed software everywhere except the banking core
Every bank has one: the engineer who is the only person who truly understands a critical system - and who is about to retire.
That's where our conversation with the IBM Z and LinuxONE Ecosystem Podcast starts. In this episode of IBM's z/Action! series, Tweezr CEO Ohad Kotler makes the case that the reason AI has transformed software development everywhere except the banking core isn't the code - it's the missing feedback loop: no machine-readable requirement, no visible dependencies, no fast tests.
What the episode covers
- Why the "retiring expert" is the real single point of failure in every core estate - and why hiring can't fix it
- The missing feedback loop that keeps coding agents guessing on a 40-year-old core
- Building a deterministic blueprint of an entire estate - COBOL, PL/I, Natural, Assembler, RPG, Java, and the distributed systems around them
- Running that blueprint on IBM Z and LinuxONE, inside the bank's own perimeter
- What becomes possible when agents finally do root-cause analysis against something they actually understand
Listen
The episode is 19 minutes, on IBM's official ecosystem channel:
- Listen on Buzzsprout
- Also on Apple Podcasts, Spotify, and Amazon Music via the IBM Z and LinuxONE Ecosystem Podcast
Want the technical background first? See how Tweezr runs on IBM LinuxONE and Linux on IBM Z.
IBM, IBM Z, and LinuxONE are trademarks or registered trademarks of International Business Machines Corporation in the United States and/or other countries.
Related Posts
The Retirement Cliff: When Your COBOL Lead Walks Out, Your Risk Doesn't
In every bank we walk into, there is one engineer who knows where the bodies are buried. When they retire, the bank inherits a system nobody can change safely. The answer is not to replace the person. It is to capture what they know - before the cliff.
Discovery Is the Migration
The industry treats discovery as Phase 1. That is the mistake that kills 70% of modernization programs. Discovery is not the prelude to the work. It is the work.
Hallucinations Under Coercion
AI doesn't hallucinate worst when it doesn't know. It hallucinates worst when a user pushes it past what it knows - and senior validators are the ones who push hardest