Iterative Retrieval Pattern

Solves the "context problem" in multi-agent workflows where sub-agents cannot predict what context they need until they start working.

When to Use

• Spawning sub-agents that need codebase context they cannot predict upfront
• Building multi-agent workflows where context is progressively refined
• Encountering "context too large" or "missing context" failures in agent tasks
• Optimizing token usage in agent orchestration

The Problem

Sub-agents are spawned with limited context. They lack knowledge of which files are relevant, what patterns exist, or what terminology the project uses.

Standard approaches fail:

• Send everything: exceeds context limits
• Send nothing: agent lacks critical information
• Guess what's needed: often wrong