Law 38 · Architecture & Operations
The Multi-Agent Tax
Every extra agent multiplies your token bill, so make sure the task can pay it.
The principle
A multi-agent research system can burn roughly 15 times the tokens of a single chat, and token usage alone can explain most of the difference in performance. So multi-agent only makes economic sense when the task is high value and the work genuinely parallelizes. For most tightly coupled work, the coordination overhead isn't worth it.
The mechanism, the warning signs, a worked example, and the apply-it recipe for this law are in the complete edition.
Unlock all 50 laws — $9.99Related laws
36
Don't Build an Agent When a Workflow Will Do
Agents buy flexibility with latency, cost, and unpredictability.
Architecture & Operations
37
Cascade Before You Escalate
Try the cheap model first. Only the hard cases deserve the expensive one.
Architecture & Operations
39
Your Architecture Mirrors Your Org Chart
You ship a system shaped like your teams, so design the teams first.
Architecture & Operations