What we're talking about when we talk about context engineering
Thoughtworks Technology Podcast
Thoughtworks
4.7 • 53 Ratings
🗓️ 2 October 2025
⏱️ 20 minutes
🧾️ Download transcript
Summary
Everyone seems to be talking about context engineering. That was certainly the case in our recent discussions for the upcoming edition of the Technology Radar (volume 33, due early November 2025). And although we ran into the term on the Technology Podcast just a few weeks ago, we thought it would be useful to try and tackle exactly what people are talking about when they talk about context engineering. We know context is important when it comes to AI, but what does it mean to engineer it?
On this episode of the Technology Podcast, host and Thoughtworks CTO Rachel Laycock is joined by Thoughtworkers Alessio Ferri (Lead Software Engineer) and Bharani Subramaniam (CTO for India and the Middle East) to discuss what context engineering is, how it's being done and what it tells us about the evolution of AI. This certainly won't be the last word — ours or anyone else's — on context engineering, but it might help clarify and cement your understanding as the term comes to dominate technology conversations.
Transcript
Click on a timestamp to play from that location
| 0:00.0 | Hello everyone and welcome to the ThoughtWorks Technology podcast. |
| 0:11.6 | I'm Rachel Leacock, the global CTO for ThoughtWorks, and I'm joined today by... |
| 0:16.2 | Burradi Subramandium. |
| 0:17.7 | Okay, and... |
| 0:18.9 | Alessi Farie. Hi, everyone. |
| 0:20.7 | I'm working to talk about a hot topic as we were putting together our technology to Bromondium. Okay, and... Alas Gaffari. Hi, everyone. |
| 0:25.5 | I'm going to talk about a hot topic as we were putting together our technology radar this week, which is context engineering. |
| 0:29.0 | We had quite a hot debate about what it was, how you define it, what's going on in the industry. |
| 0:34.1 | So I have these two special guests with me who seem to be deep efforts in this space right now, which is rare given how new it is. |
| 0:41.3 | So let's start with what is your definition of what context engineering is. |
| 0:47.1 | Okay, so context engineering is this emerging field where you curate what the model sees so that you get a better result. |
| 0:56.0 | So that is what context is genetic is for. |
| 0:59.0 | Maybe before we go into the context engineering base, I'd like to like define what the actual context is. |
| 1:04.0 | Context is this concept of providing tokens into a model so they can eventually produce an output. |
| 1:10.0 | And the engineering is all the |
| 1:12.5 | practice that sits around that and applying engineering principle to all the design of what goes |
| 1:16.9 | into this model, how we build this context, and also how do we test it. So context is actually a very broad |
| 1:24.0 | topic that could include, for example, memory, conversations, data that's |
| 1:28.1 | being accessed by an LLL. It's an umbrella term that covers everything that goes into a model |
| 1:32.9 | as it's input. So I've heard argue, though, that that is actually prompt engineering and |
| 1:40.1 | that this is just a piece of prompt engineering. So what are you, what are your thoughts on that? |
| 1:44.0 | Do you think it's a different thing? Do you think it's an piece of prompt engineering. So what are your thoughts on that? Do you think it's a different thing? |
... |
Please login to see the full transcript.
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.