Context engineering: Tackling legacy systems with generative AI

Thoughtworks Technology Podcast

Thoughtworks

Careers, Business, 907234, Technology

4.7 • 53 Ratings

🗓️ 21 August 2025

⏱️ 41 minutes

🔗️ Recording | iTunes | RSS

🧾️ Download transcript

Summary

Generative AI can be incredibly powerful when it comes to legacy modernization. Not only can it help us better understand a large, aging codebase, it can even help us reverse engineer a legacy system when we don't have access to the complete source code. Doing it, though, requires a specific approach that's being described as 'context engineering'.

This is something we've been exploring a lot in recent months at Thoughtworks. On this episode of the Technology Podcast, Thoughtworks' lead for AI-enabled software engineering, Birgitta Böckeler, and tech principal Chandirasekar Thiagarajan join hosts Ken Mugrage and Neal Ford to discuss how it works.

They explain the process, the tools and what the work is teaching them about both generative AI and legacy modernization.

Read Birgitta's blog post on reverse engineering with AI: https://www.thoughtworks.com/insights/blog/generative-ai/blackbox-reverse-engineering-ai-rebuild-application-without-accessing-code

Transcript

Click on a timestamp to play from that location

0:00.0	Hello, everybody, and welcome to another episode of the ThoughtWorks Technology podcast.
0:12.6	My name is Ken McGraich.
0:13.7	I'm one of your regular hosts.
0:15.7	We have an exciting episode today talking about experimentation that we're doing in the
0:19.8	generative AI space.
0:21.2	Co-hosting today with me is Neil Ford.
0:23.5	For the second podcast in a row, we've promised an exciting episode before we've actually said
0:28.3	anything. So we'll see if we can make that come true. And I think it's absolutely going to come
0:33.9	true today because we're talking about one of the favorite hot topics right now,
0:38.1	which is generative AI and its uses. And our first guest, Birgitta, do you like to introduce
0:43.7	yourself? Yeah, hi, I'm Begitta, Bukhler. I'm a distinguished engineer for ThoughtWorks in Germany,
0:48.5	and I'm currently a full-time subject matter expert at ThoughtWorks for using generative AI on software
0:56.2	teams and for creating software.
0:58.8	So not putting AI into a piece of software, but using it to build the software.
1:03.4	And Chandrew, you want to introduce yourself, please?
1:05.3	So I've been with ThoughtWorks since 2009, and 10 out of those 15 years, I've been with various retail accounts.
1:12.5	So I'm starting to see myself as a specialist over there.
1:15.4	So for today's episode, we're going to talk about using generative AI for one facet of
1:20.2	legacy modernization, which is one of the bigger use cases for it.
1:25.3	It's, you know, experimentation is really important overall because you really need to
1:29.5	set a goal or we can overload the term hypothesis or what have you and run tests and understand
1:36.4	and kind of the scientific method, if you will. You try something, you pass or fail, you move on.
	...

Please login to see the full transcript.

Previous episode | Next episode

Disclaimer: The podcast and artwork embedded on this page are from Thoughtworks, and are the property of its owner and not affiliated with or endorsed by Tapesearch.

Generated transcripts are the property of Thoughtworks and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.