The research harness: a one-page guide for doctoral researchers

2 min read

Guide

About this guide

The research harness framework argues that the characteristic problems of AI use in doctoral research are not problems of policy or capability; they are problems of working with an agent in the absence of a defined operating context. This guide gives doctoral researchers and supervisors a concise reference for the framework’s seven components and a practical starting point for building a harness of their own.

It condenses the harness framework into a single-page reference card for doctoral researchers and supervisors. It covers the seven components of a harness — knowledge base, interpretive permissions, tools, authority, scope register, process record, and amendment protocol — with brief descriptions of what each component does and how to start building one.

Download the guide (PDF)

Preview

Preview of the research harness one-page guide — a reference card for doctoral researchers working with AI agents

How to use it

Print or save the guide and keep it alongside your project materials. Each component has a brief description and a start prompt; a single sentence you can write to get something workable from day one. The harness doesn’t need to be complete before it’s useful; one sentence per component is enough to begin.

Discuss the harness with your supervisor. It is designed as a shared artefact: something for researcher and supervisor to negotiate together, not a private document.

The guide is derived from the full essay: The research harness: a framework for bounded AI use in doctoral work.

Continue reading

  • The research harness: a framework for bounded AI use in doctoral work

    Current responses to AI use in doctoral research locate the problem either with institutions through policy, or with students through judgement and AI literacy. This essay argues that neither response addresses the structural source of the difficulty. The characteristic problems of AI use in doctoral research are not problems of policy or capability; they are problems of working with an agent in the absence of a defined operating context. Drawing on software engineering practice, it develops the concept of the research harness: a structured specification, negotiated between researcher and supervisor, of what an AI agent is doing in a doctoral project. The harness has seven components — knowledge base, interpretive permissions, tools, authority, scope register, process record, and amendment protocol — and can be entered at a minimal level and developed iteratively alongside the work.

  • Research harness

    A research harness is a structured specification — negotiated between a doctoral researcher and their supervisor — of what an AI agent is for in a research project and how it is permitted to operate within it. It adapts the software engineering practice of harness engineering to doctoral inquiry, treating the characteristic problems of AI use in research as problems of an absent operating context rather than of policy or capability.

  • A question that replaces "did you write this?"

    Supervision has always run on an inference: if the writing is the student's, the work behind it probably is too. That's stopped holding, and detection tools don't repair it, because they're aimed at the document rather than the person. What I think breaks isn't integrity so much as calibration, which is a different, and more serious, problem to address.