Topic

#agent-trace

4 篇笔记

10-12

Agent 评测已经成为了当前 Agent应用的基石。如果说年初大家都在关注 Harness，那目前的热点和深水区，一定是 Agent评测和 Agent Infra。我所了解到的是，基本每个做 Agent 产品的组都很看重评测的方法论以及效果。因此我专门开了一个系列，给大家详细介...

x.com· 18 分钟 ·#clippings·#agent-evaluation·#eval-engineering

09-12

Everything you need to understand how an agent harness can learn from production failures and repair itself. It covers procedural memory, tr...

x.com· 12 分钟 ·#clippings·#agentic·#agent-harness

09-02

Author: René SultanAI telemetry tells us which models our agents use and what they cost, but not what we are paying them to do. We built a s...

x.com· 19 分钟 ·#clippings·#AI·#agentic

08-10

Every company is connecting Slack, email, docs and meetings into one brain that gives everyone access to everything the company knows.Nobody...

x.com· 13 分钟 ·#clippings·#agentic·#agent-permission