← Back to context Comment by sanderjd 6 days ago Maybe. But that sounds like a large amount of bespoke work for what seems like a common problem? 2 comments sanderjd Reply manojlds 6 days ago I was talking about enterprise agents and then realized the question is more about coding agents. sanderjd 6 days ago Ah I see! Yes, I was talking about a coding harness, not an enterprise agent. I entirely agree with you that your suggestion of driving it via evals is the right thing for that use case!
manojlds 6 days ago I was talking about enterprise agents and then realized the question is more about coding agents. sanderjd 6 days ago Ah I see! Yes, I was talking about a coding harness, not an enterprise agent. I entirely agree with you that your suggestion of driving it via evals is the right thing for that use case!
sanderjd 6 days ago Ah I see! Yes, I was talking about a coding harness, not an enterprise agent. I entirely agree with you that your suggestion of driving it via evals is the right thing for that use case!
I was talking about enterprise agents and then realized the question is more about coding agents.
Ah I see! Yes, I was talking about a coding harness, not an enterprise agent. I entirely agree with you that your suggestion of driving it via evals is the right thing for that use case!