AI-Assisted Research Coding

Agent Brief: Scaffold a Reproducible Research Project

Ready-made instructions for coding agents (Claude Code, Codex, Cursor...) to build an organised research project structure with configuration, experiments, tests and documentation.

Advanced Full project prompt AI agent prompt Not rated yet

Purpose of the prompt

Coding agents produce better projects when they are given clear specifications and explicit constraints. This prompt gives the agent a staged work plan and stops it from claiming success for anything it has not run.

When to use it?

When starting a new software project for a thesis or paper, or when reorganising scattered research code.

Full prompt text

Text in square brackets [ ] is a variable you replace with your research details, or fill it in from “Customise the prompt” below.

You are a research software engineer working as a coding agent inside my repository.

Project: [Project description]
Language and framework: [Language and framework]
The operating system I work on: [Operating system]
[Existing code]

Work in stages, and stop after each stage to show what you did:
1. Propose the folder structure (src, configs, scripts, tests, notebooks, data with a README explaining the data source without uploading it) and wait for my approval.
2. Set up environment management (requirements.txt or pyproject with pinned versions) and installation instructions for [Operating system].
3. A configuration system (YAML or Hydra) so that each experiment is defined by a configuration file.
4. A training and evaluation script that logs: the configuration, the seed, the code version (git hash) and the metrics to a file.
5. Fix the random seeds and split the data in a fixed, saved way.
6. Basic unit tests for data loading and the metrics.
7. A README with the exact commands to reproduce each experiment.

Strict constraints:
- Actually run every command or test before reporting that it succeeded, and show the output. If you cannot run it, say so explicitly.
- Do not delete existing files and do not modify the raw data.
- Do not put API keys or passwords in the code.
- Ask me about any unclear architectural decision.

Write your explanation in [Answer language].

Customise the prompt

Fill in only what suits you. The line of an empty optional field is removed from the final text, and empty required fields stay in brackets for you to complete later.

Optional.

Preview of the customised prompt

You are a research software engineer working as a coding agent inside my repository.

Project: [Project description]
Language and framework: [Language and framework]
The operating system I work on: [Operating system]
[Existing code]

Work in stages, and stop after each stage to show what you did:
1. Propose the folder structure (src, configs, scripts, tests, notebooks, data with a README explaining the data source without uploading it) and wait for my approval.
2. Set up environment management (requirements.txt or pyproject with pinned versions) and installation instructions for [Operating system].
3. A configuration system (YAML or Hydra) so that each experiment is defined by a configuration file.
4. A training and evaluation script that logs: the configuration, the seed, the code version (git hash) and the metrics to a file.
5. Fix the random seeds and split the data in a fixed, saved way.
6. Basic unit tests for data loading and the metrics.
7. A README with the exact commands to reproduce each experiment.

Strict constraints:
- Actually run every command or test before reporting that it succeeded, and show the output. If you cannot run it, say so explicitly.
- Do not delete existing files and do not modify the raw data.
- Do not put API keys or passwords in the code.
- Ask me about any unclear architectural decision.

Write your explanation in [Answer language].

Variables you can customise

[Project description]
Required
[Language and framework]
Optional, default value: Python 3.11 + PyTorch
[Operating system]
Optional, choose from: Windows 11, Linux, macOS, default value: Windows 11
[Existing code]
Optional
[Answer language]
Optional, choose from: Arabic, English, Arabic with English terms in parentheses, default value: Arabic with English terms in parentheses

Usage example

Example input

A project comparing CNN and ViT models for tissue image classification, Python and PyTorch, on Windows 11.

Expected output

A staged, organised project: structure, environment, configuration, logged training and evaluation, seeds, tests and a README, with actual run output.

How to use it

  • Paste the prompt into a coding agent session inside the project folder.
  • Review each stage before allowing the next one.

Tips for better results

  • Save the strict constraints in the project's instructions file (such as CLAUDE.md or AGENTS.md) so they apply in every session.

Limitations and warnings

  • Review every change the agent suggests; it may get fine research details wrong.

Suggested tools for using this prompt

Tools from the directory of research and academic publishing tools that are actually linked to this prompt's task, with the reason each tool is suggested.

Claude

Tool: Supporting Free with usage limits

A general AI assistant from Anthropic used for analysis, drafting, summarising and working with documents.

Research function: General text chat that helps you analyse texts, organise ideas and improve your wording.

Why it is suggested: A model you can use to discuss the plan before handing it to the agent.

Google Colab

Tool: Optional Free with usage limits

A hosted Jupyter Notebook service from Google that runs in the browser with no setup and offers computing resources, including GPUs.

Research function: Writing and running Python code in notebooks saved to Google Drive.

Why it is suggested: To run experiments in the cloud if no local GPUs are available.

In research workflows

Ratings

Not rated yet
Rate this prompt

One rating per visitor per prompt; submitting again updates your earlier rating. Comments appear after review.

Similar prompts