Run a systematic literature review from one prompt
SciSpace's agent generates PICO questions, searches and screens papers, downloads PDFs, extracts data and outputs the full review with a PRISMA diagram.
Done with a custom-built or unnamed agent
- What they did
- User enters the prompt at scispace.com. The agent generates PICO-based research questions and screening criteria for the user to review and edit, then lets the user select databases and date ranges. After that the agent searches papers across databases, reranks results, performs title/abstract and full-text screening, downloads PDFs, extracts data, and produces the review plus PRISMA diagram and inclusion table.
- How it went
- It outputs a complete systematic review and PRISMA diagram from a single prompt, but paywalled papers still block full automation.
- Worth knowing
- The main catch is papers behind paywalls.
Try it yourself with ChatGPT Agent
Run a systematic literature review on [research question]. Write PICO questions, search [databases, e.g. PubMed, Semantic Scholar], screen papers against inclusion criteria [criteria], and extract [data points] into a table. Finish with a written review and a PRISMA-style flow summary of how many papers were found, screened and included, and ask me to confirm the inclusion criteria before screening.
1 more account of this
Source: X · Apr 12, 2026
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
Find connections across 100 non-fiction books
Claude Code browses a personal library with CLI tools and surfaces trails of related excerpts across books.
Scrape weekly Substack rankings and write a report
Claude in Chrome runs weekly to scrape Substack ranking data into a dataset, and Cowork analyzes it and writes a weekly report.
Summarize 20 articles into a cited document
An agent extracted key insights from 20 articles, found common themes and produced a cited summary; the write-up estimates 18 minutes versus hours by hand.
Research conference speakers and organize tabs
Comet researched 50 HumanX speakers, surfaced themes and podcast guests, built a camera spec table, and cleaned up tabs.
Let Cursor maintain an Obsidian notes vault
Cursor reviews vault structure, suggests connections, answers questions about notes and writes a daily done note documenting other agent sessions.
Research content from Slack and draft Notion guide ideas
A team DM'd Lindy in Slack to summarize a year of guides and research a model, and it created a Notion guide idea after asking for approval.