Research Operator

A research operator is a thin loop around general tools. The methodology should live in skills, the math in libraries, and the case-study logic in project code.

The Problem

Hard-coding every possible research move into an agent framework creates a brittle demo. Giving the model unrestricted shell and file access creates an unauditable production risk. The useful middle ground is a narrow operator: expose a small set of typed tools, require skill discovery before implementation, sandbox writes, and stop with an evidence-backed recommendation.

The Pattern

WRONG

prompt = f"""
You are a quant researcher. Use any files and commands you need.
Try improving the case study and tell me what worked.
Task: {task}
"""
print(llm(prompt))