Tech Lead Journal30 Jun 2025

#222 - Closing the Knowledge Gap in Your Legacy Code with AI - Omer Rosenbaum

What if your most critical systems run on code that no one fully understands?

In this episode, Omer Rosenbaum, CTO and co-founder of Swimm, explains how to use AI to close the knowledge gap in your legacy codebase. Discover the limitations of AI in understanding legacy code and learn novel approaches to automatically document complex systems, ensuring their critical business logic is preserved and understood within the organization. Beyond legacy systems, Omer also shares practical advice for how junior developers can thrive in the AI era and how teams and organizations can conduct more effective research.

Key topics discussed:

How junior developers can thrive in the age of AI
The danger of shipping code you don’t fully understand
Why AI can’t deduce everything from your code alone
How writing documentation becomes more critical now with AI
How to analyze code that even LLMs struggle to read, like COBOL
How to keep your organization’s knowledge base trustworthy and up to date
The real danger of letting AI agents run unchecked
A practical approach to conducting more effective research

Timestamps:

(00:00) Trailer & Intro
(02:10) Career Turning Points
(05:24) What Juniors Should Do in the Age of AI
(11:05) Junior Developer’s Responsbility When Using AI
(14:50) AI and Critical Thinking
(16:20) Understanding & Preserving Domain Knowledge
(18:11) The Importance of Written Knowledge for AI Usage
(21:51) Limitations of AI in Understanding Knowledge Base
(26:34) The Limitations of LLM in Navigating Legacy Codebases (e.g. COBOL)
(32:38) Effective Knowledge Sharing Culture in the Age of AI
(34:54) Keeping Knowledge Base Up-to-Date
(36:55) Keeping the Organization Knowledge Base Accurate
(39:08) Fact Checking and Preventing AI Hallucination
(41:24) The Potential of MCP
(43:24) The Danger of AI Agents Hallucinating with Each Other
(45:00) How to Get Better at Research
(53:41) The Importance of Investing in Research
(57:18) 3 Tech Lead Wisdom

_____

Omer Rosenbaum’s Bio
Omer Rosenbaum is the CTO and co-founder of Swimm, a platform reinventing the way engineering organizations manage internal knowledge about their code base. Omer founded the Check Point Security Academy and was the Cyber Security Lead at ITC, an educational organization that trains talented professionals to develop careers in technology. Omer has a MA in Linguistics from Tel Aviv University and is the creator behind the Brief YouTube Channel.

Follow Omer:

LinkedIn – linkedin.com/in/omer-rosenbaum-034a08b9
Twitter – x.com/Omer_Ros
Swimm – swimm.io
Email – omer@swimm.io
📚 Gitting Things Done – buymeacoffee.com/omerr/extras
▶️ Brief – youtube.com/@BriefVid

Like this episode?
Show notes & transcript: techleadjournal.dev/episodes/222.
Follow @techleadjournal on LinkedIn, Twitter, and Instagram.
Buy me a coffee or become a patron.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(282)

The IT/OT Handbook: From Silos to Sustainable Digitalization - David Ariens & Willem van Lammeren

Why can’t you “move fast and break things” in a factory? Because a small software bug doesn’t just crash an app, it can shut down a plant the size of a small city. David and Willem explain the hidden ...

28 Sep 1h 7min

Don't Outsource Your Thinking: How to Lead in the AI-Native Era - Emilie Schario

What’s the one rule that matters most when AI writes most of your code? Emilie says it comes down to a single line: don’t outsource your thinking.In this episode, Emilie Schario, co-founder of Kilo Co...

7 Sep 59min

The Father of AI Assistant on Why Joy Comes Before Success - Kevin Surace

If you’re not using AI five times an hour, you’re already behind, says the man who built the first AI assistant back in 1998. Kevin explains why that pace is now the baseline, not the exception, for d...

24 Aug 55min

Software Engineering Laws Every Developer Must Know in the AI Era - Milan Milanovic

Does moving faster with AI mean you get to skip the laws that governed every software project before it? Milan Milanovic argues the opposite, the old laws of software engineering now apply twice as ha...

10 Aug 1h 1min

Signals & Levers: Systems Thinking to Navigate Software Delivery Illusions - Elisabeth Hendrickson & Joel Tosi

(04:48) Brought to you by SpeechifyAITired of text-to-speech that sounds robotic or costs too much at scale? SpeechifyAI's new Simba 3.2 model ranks #1 on Artificial Analysis for realness, priced unde...

3 Aug 1h 17min

From Technical Debt to Triple Debt: The Hidden Cost of AI-Generated Code

Is vibe coding quietly draining the thing that makes teams effective: their shared understanding? Margaret breaks down her new “triple debt” model, and why cognitive debt might be the one nobody’s tra...

27 Jul 1h 10min

Ex-Gojek CTO: Why the Age of AI Rewards Builders as Judgment Becomes Expensive

If expertise is becoming almost free, why is judgment becoming the most expensive skill in tech? Ajey Gore, former Gojek CTO, explains why the age of AI agents rewards builders over typists.In this ep...

13 Jul 1h 22min

The AI Productivity Paradox: Why 10X Output Doesn't Mean 10X Business Outcome

What if optimizing for AI output is actually slowing your company down? When code becomes nearly free to produce, the organizations still measuring productivity by output are solving the wrong problem...

29 Jun 1h 5min