How to Write AI Prompts for Academic Research
Watch the tutorial37 min
TL;DR
Learn to prompt an AI research agent with the CORE framework for structured literature reviews, and how file formats and context affect results.
Who it's for
This session is for researchers, PhD students and academics who use SciSpace Agent and want more specific, less generic output.
What you'll learn
- The CORE prompt framework: Context, Output, Role and Exclusions, with examples such as asking the agent to act as a peer reviewer or to limit databases and dates.
- A live comparison of a lazy prompt and a CORE prompt for a literature review, ending in Deep Search results and a DOCX literature review.
- How one line in a prompt makes SciSpace Agent plan before it runs a task, followed by a run that includes a literature search, an image and an ROI report.
- Which file formats work best as agent inputs, with a test showing that a DOCX upload used about 3.5 times the credits of the same content in Markdown.
- How to name and describe attachments so the agent reads only the relevant files.
- What a context window is, why to trim PDFs before uploading, and when to start a new thread.
Steps shown in the video
How to give an AI agent context and specify the output format
How to name and describe uploaded files for an AI agent
Chapters
- Why does an AI research agent give generic answers?
- What is the CORE prompt framework for AI agents?
- How to give an AI agent context and specify the output format
- Role and exclusions in AI prompts: peer reviewer, databases, dates
- Lazy prompt for an AI literature review: what goes wrong
- Writing a CORE prompt for a structured literature review
- Why tell an AI agent what to exclude, not what to include?
- CORE prompt results: Deep Search and a DOCX literature review
- Why AI agents should plan before running a research task
- The one line that makes SciSpace Agent plan first
- Watching the agent run its plan: literature search, image, ROI report
- Which file formats work best as AI agent inputs?
- DOCX vs Markdown upload: 3.5x credit difference
- How to name and describe uploaded files for an AI agent
- Describing attachments so the agent reads only relevant files
- What is an AI agent's context window?
- When should you start a new chat with an AI agent?
- Trim PDFs before uploading for better AI output
- Start a new thread for every new task
- Recap: five tips for better results from an AI research agent
Questions this video answers
What is the CORE prompt framework for AI agents?
The CORE prompt framework: Context, Output, Role and Exclusions, with examples such as asking the agent to act as a peer reviewer or to limit databases and dates.
Watch this part of the tutorialWhy tell an AI agent what to exclude, not what to include?
Key takeaways: tell the agent what to exclude, not only what to include.
Watch this part of the tutorialWhich file formats work best as AI agent inputs?
Which file formats work best as agent inputs, with a test showing that a DOCX upload used about 3.5 times the credits of the same content in Markdown.
Watch this part of the tutorialWhat is an AI agent's context window?
The CORE prompt framework: Context, Output, Role and Exclusions, with examples such as asking the agent to act as a peer reviewer or to limit databases and dates.
Watch this part of the tutorialWhen should you start a new chat with an AI agent?
What a context window is, why to trim PDFs before uploading, and when to start a new thread.
Watch this part of the tutorialDo this in SciSpace
Do this in SciSpaceRelated tutorials
EN29:04TutorialBuild an AI-Driven Research Workflow: Your Academic Second Brain
Dr. Olarik Musigavong shows how to use SciSpace as an academic second brain for discovery, knowledge management and drafting.
EN36:07TutorialSciSpace Agent Guide: Use Cases, Demos and Research Best Practices
A hands-on tour of SciSpace Agent across discovery, paper analysis, writing, data work and grants, with practical starting points.
PT32:41TutorialIA para professores: aulas, orientação e pesquisa com o SciSpace
Veja como professores e orientadores podem usar o SciSpace para planejar aulas, apoiar orientandos e fortalecer a própria pesquisa.
