#agent-design
Every post tagged "agent-design".
112 posts · showing 111–112
-
The Supervisor That Became a Bottleneck: When Not to Add a Second Agent
Splitting a task across agents adds a boundary, and every boundary quietly drops context. Here's the test for whether your second agent is buying isolation or just paying double for a worse answer.
-
Why Your Agent Forgets Step 2 by Step 7 — And Four Ways to Keep the Thread
Agents rarely fail because they reason badly — they fail because the original instruction gets buried under accumulated tool output. Here's how to tell displacement from dilution, and four fixes that keep the thread intact.