What is harness engineering?
Thoughtworks Technology Podcast
Thoughtworks
4.5 • 58 Ratings
🗓️ 14 May 2026
⏱️ 41 minutes
🧾️ Download transcript
Summary
'Harness engineering' is one of the most significant terms to emerge in software engineering in 2026. Broadly referring to the work done to control unpredictable AI agents and coding assistants, its use signals growing attention on what needs to be done to make agents reliable and consistent enough for production software in the real-world.
On this episode of the Technology Podcast, Birgitta Böckeler joins hosts Prem Chandrasekaran and Nate Schutta to explore what harness engineering actually is, how it should be done and why it should matter to software engineers working today. Having written a number of articles on harness engineering for martinfowler.com based on her experiences with AI-assistance, Birgitta is well-placed to explain the core concepts and implications.
Taking in everything from the practices and ideas that pre-date and inform harness engineering to integrating harness engineering into existing workflows, listen for a conversation that will provide much needed clarity on what's an essential topic in the industry.
Read Birgitta's article on harness engineering on martinfowler.com: https://martinfowler.com/articles/harness-engineering.html
Watch Birgitta's video on harness engineering beyond skills on YouTube: https://www.youtube.com/watch?v=uLWOLmeHOSE
Transcript
Click on a timestamp to play from that location
| 0:00.0 | Welcome everyone to yet another episode of the ThoughtWorks Technology podcast. |
| 0:12.9 | My name is Prem Chandar Shaker. |
| 0:14.6 | And today I've got my co-host, Nate Schuter. |
| 0:18.5 | Nate, we want to quickly introduce yourself. |
| 0:20.4 | Absolutely. I'm Nate Shoe, the best way to describe me as architect as a service here at ThoughtWorks. |
| 0:25.0 | All right. And today we are joined by Brigitte Bocler, who is usually a host on the ThoughtWorks Technology podcast. |
| 0:32.4 | But today she's playing the role of a guest. and she recently wrote an article on something that's |
| 0:41.2 | called harness engineering for coding assist agent users on martin fowler.com so for me that was the |
| 0:49.6 | clearest mental model that I've seen for what teams running coding assistance day to day should |
| 0:55.6 | actually use to build around them. Welcome, Brigida. Do you want to quickly introduce yourself as |
| 1:02.2 | well? Yeah, hi, Prem and Nate. Yeah, I'm Begitta. I'm a distinguished engineer at ThoughtWorks, |
| 1:07.2 | and I'm based in Berlin and Germany. And I have been a host in the past indeed, |
| 1:12.1 | but I haven't been on the podcast in a while, so I'm glad to be back. |
| 1:16.2 | So before we get into definitions and such, here's the question that I would want users |
| 1:22.8 | to keep their heads the whole time. |
| 1:25.7 | So if you're running a coding agent, CloudCode, Cursar, co-pilot, every day, |
| 1:31.3 | and you feel the gap between what these tools can produce |
| 1:35.3 | and what you would actually trust |
| 1:37.3 | without supervision in some cases. |
| 1:40.3 | This episode really, for me, is about closing that gap. |
| 1:45.1 | So let's start at the beginning, right? |
| 1:48.2 | What is our harness engineering and why are you writing about it now? |
... |
Transcript will be available on the free plan in 7 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 2026.