“This might be a bit of a bold statement, but an agent without evals is a proof of concept. This doesn't matter what infrastructure it's been deployed on to. If you do not have evaluations, you cannot confirm for sure that the agent is behaving as expected.”
Thoughts from the Practical AI Show covering the event ‘Abundant Intelligence at the Midwest AI Summit’
ABitcoinGuy / CWM
npub1qm…2sswt
2026-10-31 08:36:16 UTC
Author Public Key
npub1qm8ltd4njp8lpr0r8hdkgm3kfrz5zgsjwnkdw0kjwf2xj9awrlhsn2sswtPublished at
2026-10-31 08:36:16 UTCEvent JSON
{
"id": "96e27e0bce88841978c7cf4f95d1f66791486c1983ceebf750584fe19ff112f0",
"pubkey": "06cff5b6b3904ff08de33ddb646e3648c541221274ecd73ed272546917ae1fef",
"created_at": 1793435776,
"kind": 1,
"tags": [
[
"client",
"Primal iOS"
]
],
"content": "“This might be a bit of a bold statement, but an agent without evals is a proof of concept. This doesn't matter what infrastructure it's been deployed on to. If you do not have evaluations, you cannot confirm for sure that the agent is behaving as expected.”\n\nThoughts from the Practical AI Show covering the event ‘Abundant Intelligence at the Midwest AI Summit’",
"sig": "db49867630341dea23d00a6b6714bbb8af17616374b31a03f7b6e797d9375b33b5a9866a5b3e950602e6455ba0795ce22058abe9393fab0866f27d3de9aeb300"
}