We provided our harness with a single objective - 2048 with a twist - and 2 days later it delivered.

https://github.com/awesoftsolutions/idea_meta-muse-2048-game

The run is recorded end to end, so the code can be checked against the process that produced it. Our app is drivable via replay here: https://favur.dev/go/drive/the2048

We took loop engineering a step further and run the agents inside workflows to keep them on task across the whole 2 day run. Happy to get into how it works.