#222 - Closing the Knowledge Gap in Your Legacy Code with AI - Omer Rosenbaum
Tech Lead Journal30 Kesä 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:


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.

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(279)

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

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 Elo 1h 1min

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

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 Elo 1h 17min

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

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 Heinä 1h 10min

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

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 Heinä 1h 22min

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

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 Kesä 1h 5min

The Hidden Stories Sabotaging Your Culture Change

The Hidden Stories Sabotaging Your Culture Change

Why do 70% of change efforts fail — even when leadership is fully committed? The answer isn’t strategy or resources; it’s the hidden stories people unknowingly carry that silently block every initiati...

15 Kesä 1h 8min

Creator of Meta's Hack: Your AI Will Always Cheat — Here's How to Stop It

Creator of Meta's Hack: Your AI Will Always Cheat — Here's How to Stop It

What if your AI coding agent is quietly cheating on your tests — and how do you stop it? Julien Verlaguet, who built the type system Meta used to migrate tens of millions of PHP lines, is now building...

8 Kesä 1h 18min

Eric Ries: Why Good Tech Companies Go Bad, and How to Stop It

Eric Ries: Why Good Tech Companies Go Bad, and How to Stop It

Why do companies with the best intentions end up betraying their customers, employees, and mission? Eric Ries calls it “financial gravity” — an invisible force that pulls even the most principled comp...

1 Kesä 1h