Agents

Shift archive

Hugging Face's project account makes the case for specifying a baseline, spending approval and a check that training changed the weights.

RMRafael Moura1 min read

ServiceNow's pipeline turns capability gaps into executable tasks, checking both successful trajectories and incorrect outcomes.

RMRafael Moura1 min read

Liquid AI documents local agent integration; the application still needs to own permissions and tool execution.

RMRafael Moura1 min read

Executable outcome checks become training rewards. The reported gains in repeatability come with limits on coverage and transfer.

RMRafael Moura1 min read

IBM’s comparison shows why orchestration deserves scrutiny—and why a benchmark result needs its configuration attached.

RMRafael Moura4 min read

Hermes documents separate ways to retain guidance, retrieve reusable methods and inspect the conversations behind a decision.

RMRafael Moura4 min read

Harness Hub explores environment-specific adapters, with evidence tied to the tested model and execution setup.

RMRafael Moura1 min read

The v0.23.0 release centralizes session continuity while leaving web access off by default.

RMRafael Moura1 min read