Using generative AI for legacy modernization
Thoughtworks Technology Podcast
Thoughtworks
4.7 • 53 Ratings
🗓️ 28 November 2024
⏱️ 33 minutes
🧾️ Download transcript
Summary
Legacy modernization is an enduring challenge — and as systems become more complex, the difficulty of understanding and modelling a system so it can be modernized only becomes more difficult. However, at Thoughtworks we've seen some recent success bringing generative AI into the legacy modernization process.
To discuss what this means in practice and the benefits it can deliver, host Ken Mugrage is joined by Thoughtworks colleagues Shodhan Sheth and Tom Coggrave. Shodhan and Tom have been working together in this space in recent months and, in this episode of the Technology Podcast, offer their insights into finding success with this novel combination. They explain how it can be implemented, the challenges and experiments they did on their way to positive results and what it means for how teams and organizations think about modernization in the future.
Read Shodhan and Tom's article on legacy modernization and generative AI (written with Alessio Ferri): https://martinfowler.com/articles/legacy-modernization-gen-ai.html
Transcript
Click on a timestamp to play from that location
| 0:00.0 | Hello, everybody. Welcome to another edition of the ThoughtWorks Technology podcast. |
| 0:12.1 | My name is Ken McGreg. I'm one of your regular hosts. |
| 0:15.0 | I had a little bit of a special edition this time. I'm at the Microsoft Ignite show. |
| 0:20.0 | So we're recording this here in late November and was |
| 0:22.5 | lucky enough to coincide with the schedules of a couple thought workers. I think you'll find |
| 0:28.3 | interesting. So today we're going to talk about some legacy modernization meets generative AI. |
| 0:34.9 | My guest today, Tom Coggrove, Tom, you want to introduce yourself? |
| 0:39.4 | Yep. Hi, folks. My name's Tom Cograve. I'm a technologist here at ThoughtWorks, where I'm |
| 0:44.1 | looking to how we can speed up a way in which we do modernization for our clients, |
| 0:49.5 | and particularly looking into mainframe modernization of late. Great, thanks. And Showdown, |
| 0:54.0 | chat. Do you want to do yourself, |
| 0:55.1 | please? Yeah. So I also am in technologies at Thoughtworks and play a similar role to Tom and also |
| 1:01.6 | focus on all the things legacy modernization. Great. So, you know, one of the common jokes here at |
| 1:07.8 | any large event is, you know, don't play a drinking game around the word |
| 1:13.0 | AI or the phrase AI because you won't survive. And so we know everybody was flooded with AI, |
| 1:18.5 | but you all are doing some really interesting hands-on practical work that's actually been going on |
| 1:24.1 | for quite some time now. So, you know, can we say, for understanding the shift, how is generative AI helping you comprehend |
| 1:31.8 | these complex, longstanding code bases for modernization? |
| 1:35.5 | I guess when you think about an existing kind of legacy code base, we're talking about |
| 1:41.1 | something that's maybe 20, 30, 40 years old, likely kind of |
| 1:44.6 | in the 40, in the kind of many millions of lines of code. And so one of the problems with that |
| 1:50.4 | is, I guess, the amount of time it takes humans or individuals to actually kind of get through |
... |
Transcript will be available on the free plan in -121 days. Upgrade to see the full transcript now.
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.
Copyright © Tapesearch 2025.