Agents

Agent guardrails without lobotomizing the agent

Agent guardrails without lobotomizing the agent

Adding guardrails to an agent is one of those task ...

Tool selection: when the model should pick, and when you should

Tool selection: when the model should pick, and when you should

Tool-using agents look powerful in demos because t ...

Evaluating agents when there's no single right answer

Evaluating agents when there's no single right answer

Evaluating a single prompt is hard. Evaluating an ...

Planner-executor splits: when to separate them

Planner-executor splits: when to separate them

A single model doing both planning and execution f ...