Agents
Agent guardrails without lobotomizing the agent
- William Jacob
- Safety , Agents
- 13 May, 2026
Adding guardrails to an agent is one of those task ...
When the agent fails: recovery patterns that don't loop forever
- Sam Wilson
- Reliability , Agents
- 12 May, 2026
Agent failures don't throw exceptions. They produc ...
Tool selection: when the model should pick, and when you should
- William Jacob
- Tools , Agents
- 10 May, 2026
Tool-using agents look powerful in demos because t ...
Evaluating agents when there's no single right answer
- William Jacob
- Evaluation , Agents
- 05 May, 2026
Evaluating a single prompt is hard. Evaluating an ...
Planner-executor splits: when to separate them
- Sam Wilson
- Architecture , Agents
- 03 May, 2026
A single model doing both planning and execution f ...