You can now run any Dockerfile on Vercel.
# 𝙳𝚘𝚌𝚔𝚎𝚛𝚏𝚒𝚕𝚎.𝚟𝚎𝚛𝚌𝚎𝚕
𝙵𝚁𝙾𝙼 𝚐𝚘𝚕𝚊𝚗𝚐:𝟷.𝟸𝟺
𝙲𝙾𝙿𝚈 . .
𝚁𝚄𝙽 𝚐𝚘 𝚋𝚞𝚒𝚕𝚍 -𝚘 /𝚜𝚎𝚛𝚟𝚎𝚛 .
𝙲𝙼𝙳 ["/𝚜𝚎𝚛𝚟𝚎𝚛"]
https://t.co/xOUMi4zxpD
This is what I want from agent evals:
- Did it call the right tools?
- Did it avoid the dangerous tool?
- Did it say the right thing?
Also: no separate eval universe. Just scripts against the real agent runtime.