Human-in-the-loop: design for the handoff, not the override

Most human-in-the-loop systems are built as if the human is a backstop — present to override the mod ...

Evaluating agents when there's no single right answer

Evaluating a single prompt is hard. Evaluating an agent that runs ten tool calls before answering is ...

Agent memory: episodic, semantic, and what to keep

The first agent you build has no memory beyond the current conversation, and that works for about a ...

Memory strategies for long-running agents

Long-running agents accumulate context. The job of memory design is to decide which slices of that c ...

When the agent fails: recovery patterns that don't loop forever

Agent failures don't throw exceptions. They produce plausible-looking output that's wrong, or quietl ...

Multi-agent systems: coordination is the actual hard part

Multi-agent architectures are seductive because they map onto how humans organize work: specialists, ...

Planner-executor splits: when to separate them

A single model doing both planning and execution feels elegant on day one. By month three, the trace ...

Designing an agent harness that doesn't fight the model

Lorem ipsum dolor sit amet consectetur adipisicing elit. The harness around an agent matters more th ...

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

Tool-using agents look powerful in demos because the model is choosing what to do next. They look fr ...

ReAct in production: reasoning that survives sidetracks

ReAct is a clean idea: think, act, observe, repeat. In production, the loop is the part that breaks. ...

Categories
Tags