Research
Agents that search papers and sources, read them in depth and write cited summaries or literature reviews.
39 published use cases
A Slack agent answers enrollment and coursework questions from your Notion handbook, cites the page, and tags staff when it is unsure.
Grok Bot roles read new papers and extract claims, rerun analyses, and scan sources, working overnight to produce briefs.
Original post ↗Poster gave a Claude Code agent access to about 2M papers to search before each attempt; it found techniques it otherwise wouldn't know and beat a baseline agent.
Original post ↗Scheduled scripts produce a daily arXiv digest, and a nightly script launches Claude Code agents to summarize each saved PDF into a notes folder.
Original post ↗Author built a proof-of-concept app using ChatGPT prompt templates to grade papers, generate lesson plans, and give feedback.
Original post ↗Poster built an agent skill that starts from seed papers, searches backward and forward, screens candidates, and iteratively refines a literature review.
Original post ↗A commenter had Claude Code write file-by-file summaries of non-obvious methods in a research project, then reviewed them to keep track of the work.
Original post ↗A commenter built a custom browser agent to research and download scientific papers, and also uses browser agents for controlled data entry.
Original post ↗A teacher's co-teacher uses ChatGPT to create assignments and tests, with commenters also using it to grade papers and create texts.
Original post ↗A reply describes daily and weekly cron jobs running AI deep research on watchlists and monitoring company events and insider activity.
Original post ↗A teacher says Claude Cowork saved hours on curriculum design, grading papers, making PowerPoints, and analyzing student grades.
Original post ↗Poster recommends a research-focused tool that does systematic review (slow but strong), adds notes to papers, and builds a research project over time.
Original post ↗Author used ChatGPT to summarize and structure a thesis literature review, and tried a tool that builds summaries from real papers to avoid invented citations.
Original post ↗Author used ChatGPT Deep Research and Agent Mode for research help and writing assistance while writing an academic social science paper.
Original post ↗SciSpace's agent generates PICO questions, searches and screens papers, downloads PDFs, extracts data and outputs the full review with a PRISMA diagram.
Original post ↗Comet found major LLM/agent training papers from six months with links and analysis, then saved them to a Word doc via Outlook.
Original post ↗Forum users write papers in markdown with Zotero citations and a bibtex file for Cursor to pick references from, converting to Word with pandoc.
Original post ↗An n8n workflow extracts metadata from new PDFs, finds related papers on Semantic Scholar and PubMed, builds an APA citation, logs to Sheets and creates a Notion summary.
Original post ↗An n8n workflow turns a topic into up to three Tavily searches, compiles a Markdown report with an agent, and pushes it to a Notion page.
Original post ↗ChatGPT Agent searched academic databases for recent open-access empirical papers, grouped them by field, wrote an annotated bibliography, noted research gaps and assembled a draft.
Original post ↗Author uses ChatGPT Deep Research with detailed family prompts to find destinations, attractions and schedule trips; it can't yet filter and book accommodation.
Original post ↗A researcher used Claude Code as the main agent to build data pipelines and do the data analysis for a paper, generating over 98% of the code.
Original post ↗Cursor Agent writes and maintains interlinked markdown pages from user-supplied sources, summarizing and cross-referencing, with Obsidian used to browse.
Original post ↗An n8n workflow fetches arXiv papers daily for a keyword, summarizes them with Gemini 2.5 Flash, writes them to Notion and sends Feishu and Gmail notifications.
Original post ↗An OpenClaw agent runs a YouTube summariser and a paper-condensing tool, saving Markdown into two indexed knowledge bases for videos and papers.
Original post ↗Codex reads a folder of PDFs to find articles that disagree with an argument, screens about fifty papers for a systematic review, and cleans messy CSV or Excel files.
Original post ↗Claude Code writes the SQL and vector queries against a public read-only index, and can set email alerts for nuanced criteria.
Original post ↗A weekly Codex automation searches arXiv for keywords, logs new papers to a CSV, sorts them into keep/skim/drop buckets and can check claims against Zotero.
Original post ↗A Manus agent connected to Heurist's mesh ran deep research on US stablecoin adoption in 2026 after one approval step, finishing in two minutes.
Original post ↗A setup of 10 specialized Grok Bot agents includes a Research agent that finds sources and data and a Deep Research agent that compares sources into insights.
Original post ↗Students reportedly direct AI agents to log into Canvas and Blackboard to take quizzes, watch lectures, write papers and post in discussions.
Original post ↗Feynman multi-agent system searches papers and the web, synthesizes findings, runs simulated peer review, verifies citations, and outputs a cited brief.
Original post ↗An agent sent firm follow-ups every 48 hours, built a paper trail and prepped a regulator grievance; the $1,200 flight refund was processed within a week.
Original post ↗Answer.AI had Devin fetch an author's recent papers and research transcript summarization; it got stuck parsing HTML and returned generic results, rated a failure.
Original post ↗The author built a pipeline with Gemini Deep Research, NotebookLM and Sheets that produces a scored lead profile and outreach draft in under 20 minutes, tested on three companies.
Original post ↗A researcher uses Claude to search Google Scholar, follow citations, query a Zotero library in natural language, and write summary notes into Zotero or Obsidian.
Original post ↗A cookbook shows a GitHub bot that triages issues, reviews PRs, answers questions with citations, flags AI-slop contributions, and opens patch PRs for human review.
Original post ↗Claude Code, guided by a CLAUDE.md, searches research papers, scans and PDFs via Spotlight, extracts text, and files daily notes in dated folders.
Original post ↗A paper on autonomous mathematical discovery in an open-world multi-agent environment.
Original post ↗Use agents that cite the exact source for each claim, and open the paper when a finding matters. Summaries are a fast way to decide what to read in full, not a replacement for reading the methods.
Across the 39 published workflows on this page, the most used tools are Claude Code (6), ChatGPT (4) and n8n (3). Each use case lists every tool it needs and the role it plays.
Open any use case to see the tools, the step-by-step setup and example prompts you can copy. Start with a beginner workflow, run it on a small batch and review the output before you automate it fully.