Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Agent harnesses explained in <90 seconds. TLDR: if you’re not working on the model, you’re working on the harness.

15,584 Aufrufe • vor 11 Tagen •via X (Twitter)

8 Kommentare

Profilbild von 安叫兽|Bird🕊️ 🔶 BNB
安叫兽|Bird🕊️ 🔶 BNBvor 11 Tagen

模型还没搞明白,套件先学会了也挺真实的

Profilbild von Matthew
Matthewvor 11 Tagen

What's going ond Sounds like someone's trying to describe a new way of understanding something!.

Profilbild von Ramanu Henri Jan
Ramanu Henri Janvor 11 Tagen

@grok comment faire une vidéo comme ça

Profilbild von Anima
Animavor 11 Tagen

The harness distinction is key - reliability, permissions, and tool loops are where agent products become usable.

Profilbild von AgentAllowlist
AgentAllowlistvor 11 Tagen

Yes. We spent months in the harness and the thing that kept biting us was the agent opening pages it had no business opening. No harness had a map of the web, so we built one. AI agent allow list: 40M domains, 28 page types, login, checkout and upload denied before the tool call.

Profilbild von Yi Casillas
Yi Casillasvor 11 Tagen

这句很到位,模型会换,但上下文、工具和失败处理才是最磨人的那层。

Profilbild von Ricardo 👺
Ricardo 👺vor 11 Tagen

this harness vs model split is so real right now. most teams i see shipping agents are just fighting the orchestration, memory, tool calling and eval loop anyway. the model is almost becoming a commodity at this point. good explainer tho, gonna check that academy course later.....

Profilbild von SOP | AI Agent Builder
SOP | AI Agent Buildervor 11 Tagen

A harness becomes production-grade when each run emits a replayable trace: model and tool versions, arguments, state transitions, latency, cost, and evaluator verdict. Keep a small failure corpus in CI so harness changes are tested against regressions, not just happy-path demos.

Ähnliche Videos