← All IntelClip / OtherPrompts as domain-specific 'paper cuts' and the value of agent companies
From The State of Model Routing — NVIDIA, Cognition, OpenRouter · ≈40:11
“the value of an agent company like the value of Devin is all these like doom loops that you've discovered that are across all industries and the best ways to recover from them”
“anyone can like like any engineer or any like agent can inspect the traces and like adjust the prompt and then see the like live accuracy”
“the prompt is part of the the startup building process and is also really easy to observe and like and have and have like multiple people and agents collaborating on them”
What’s in it
- Argues an agent startup's real moat is cataloged failure patterns, not code
- Frames prompt engineering as a core, observable part of building agent startups
- Describes inspecting live traces to tune subtask and advisor-model prompts
Clip transcript
>> Yeah, um well, I think with building agents, there are all kinds of paper cuts and edge cases that are domain-specific and like the value of an agent company like the value of Devin is all these like doom loops that you've discovered that are across all industries and the best ways to recover from them and like man here I mean it manifests big time in what the prompts are going to be both for like you know how the the advisor model gets called um uh you know the smart friend >> [laughter] >> the how the like subtask agents get called and and the best thing is that like anyone can like like any engineer or any like agent can inspect the traces and like adjust the prompt and then see the like live accuracy long time. So I mean basically I just think that that's part the prompt is part of the the startup building process and is also really easy to observe and like and have and have like multiple people and agents collaborating on them.
Comments
Sign in to comment.
Loading comments…