Architecture
The Agent Harness: Why Your Model Isn't the Problem
- William Jacob
- Agents , Architecture
- 11 May, 2026
LangChain jumped from outside the top 30 to number 5 on TerminalBench 2.0. They didn't change the mo ...
How autonomous is too autonomous
- John Doe
- Architecture , Autonomy
- 06 May, 2026
Autonomy in agents is a slider, not a switch, and the right setting depends on the task more than th ...
Agent memory: episodic, semantic, and what to keep
- Sam Wilson
- Architecture , Memory
- 05 May, 2026
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
- John Doe
- Architecture , Multi Agent
- 03 May, 2026
Multi-agent architectures are seductive because they map onto how humans organize work: specialists, ...
Planner-executor splits: when to separate them
- Sam Wilson
- Architecture , Agents
- 03 May, 2026
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
- John Doe
- Harness , Architecture
- 02 May, 2026
Lorem ipsum dolor sit amet consectetur adipisicing elit. The harness around an agent matters more th ...
ReAct in production: reasoning that survives sidetracks
- John Doe
- Architecture , ReAct
- 01 May, 2026
ReAct is a clean idea: think, act, observe, repeat. In production, the loop is the part that breaks. ...