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 than the model behind it. A well-shaped harness can elevate a mediocre model; a clumsy one can ruin a great one.

Loop shape and termination

Nam ut rutrum ex, venenatis sollicitudin urna. Aliquam erat volutpat.

Excepturi repellendus consequatur quibusdam optio expedita praesentium.

Integer eu ipsum sem.

How autonomous is too autonomous

Autonomy in agents is a slider, not a switch, and the right setting depends on the task more than th ...

The Agent Harness: Why Your Model Isn't the Problem

LangChain jumped from outside the top 30 to number 5 on TerminalBench 2.0. They didn't change the mo ...

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 ...

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 ...

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. ...

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 ...

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 ...

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 ...

File-Based Agents Don't Need a Build Step

The investment banking analyst who spends Friday night formatting a pitch deck isn't doing analysis. ...