ashish004

What is the major advantage of this versus using conductor / cmux / intent / amp ? Also, versus claude code over rc (remote-control)

Out of all AI slops, this is best one and depicts what Dario's AI (Claude) is capable of.

True. Thats exactly what we have done. Once finalrun is installed, it ships all the skills to generate and run the test from the same repo.

Saw the website https://clawd.rip, pretty cool and informative.

Hey, thats true, verification of ai generated code needs proof with video of each action, console logs and network logs. Would love to know how you are solving for web. would be a great learning for me too.

Do share us feedback.

Just updated README.md, it's lot simpler and addresses on the core. Thanks for the feedback, please checkout

Yes gavinray, It gets persisted to the project. Its lives alongside the codebase. So that any test generated has the best context of what is being shipped. which makes the AI models use the best context to test any feature more accurately and consistently.

Hi Avikaa, finalrun provides skills that you can integrate with any IDE of your choice. You can just ask the finalrun-generate-test skill to update all the test for your new feature.

We have built a QA agent that can understand your plain english intent and uses vision to reason and navigate the app to test your intent. You can check our benchmark here https://finalrun.app/benchmark/ and how we architected our agent for the benchmark https://github.com/final-run/finalrun-android-world-benchmar.... Its all open source