Real AI agent use cases, with sources and setup prompts
Literature reviews, math runs, simulations and paper tracking people handed to AI agents, each linked to the original post. 17 matching use cases below, each with a public source.
Looking for something else? Search all 954 use cases or .
A team open-sourced more than 280 research agent skills aimed at the ways agents fail at academic work: invented citations, generic writing and ignoring current journal rules. They install with one npx command into Claude Code, Codex, Cursor, Gemini CLI and more.
Instead of stopping work to watch Claude Code click around his own browser, a creator gave the agent its own logged-in space in the browser with ego (lite), so it runs a research task while he keeps writing.
After catching fake references in answers that looked perfect, a builder made a connector that makes the AI verify every reference against Crossref, PubMed and OpenAlex before showing it, and flag retracted papers.
A creator ran an autonomous science workflow in Claude Code for three days straight, with Codex driving it and checking the evidence each round. The loop is open source on GitHub.
An engineering team told an AI agent to run an Abaqus simulation from one line: it built the model, meshed it, ran the job and checked the results against hand calculations. They open-sourced 7 skills that teach Claude Code, Cursor, Codex and Gemini CLI to build models, fix meshes, set up drop tests and extract results.
A security researcher used REA, Ghidra and Codex to statically analyze a Windows loader without ever executing it.
The author set scheduled tasks for Grok Bot to track papers on robotic self-improvement and save them to Google Drive automatically.
Auto Research tracks community pull requests that improve the key numbers in OpenAI's 2026 math preprints, starting with integer multiplication below n log n. It gives you a copyable prompt to point Codex or Claude Code at the latest bound, test an improvement and submit a reproducible contribution.
A researcher keeps an "LLM wiki" with 399 knowledge nodes that runs as a single agent skill, giving agents persistent memory without flooding their context. He built it while using Claude Code to research coding agents like Claude Code, OpenCode, Pi and Aider, and links findings to papers.
A patient wrote up everything she built since March after Anthropic gave her $30,000 in Claude credits to research her own tumor. She is now looking for someone who can manufacture a personalized vaccine and a hospital that can give it.
A team vibe coded Gewu Insight, a workspace for finding, organizing and reading research papers with support for AI assistants.
Anima is a Claude Code skill that turns a biology idea (dopamine receptors, stimulants, semaglutide) into an interactive isometric figure with toggleable mechanisms and a citation for every number on screen.
Anthropic gave Claude plain-language specs for eight quantum circuits from chemistry, optimization, physics and number theory plus an evaluator that checks and scores each design. Working largely on its own, Claude beat the best published circuits, in some cases by an order of magnitude or more.
Upload key journal articles, seminal and recent studies to NotebookLM and synthesize a focused literature foundation for a paper.
Describe your research question in Elicit; it finds papers, extracts findings and builds your literature review table.
Paste a prompt into Claude Code that gives it read-only SQL and vector access to 600 GB of Hacker News, arXiv, LessWrong and more.
rStation is a research community where independent AI agents discuss problems such as the Riemann hypothesis and Epoch AI challenges and publish reviewed papers, while humans watch.
How to make faceless YouTube videos with AI · How to automate work with n8n and AI · How to vibe code an app with Claude Code · How to build AI agents for SEO and ads · How to run multiple coding agents together · How to build an MCP server for AI agents · How to add memory to coding agents · How to secure vibe-coded apps and agents · How to observe and debug AI agents · How to build agent memory and context layers · How to control coding agents from your phone · How to add payments to vibe-coded apps · How to run local LLMs with AI agents · How to set up Grok Bot agents for real work · How to build with Gemini 4 Argon and Gemini agents · How to use AI agents for taxes, bills and budgets · How to make AI video ads and Reels with agents · How to set up Hermes Agent workflows · How to vibe code a game with AI · How to replace SaaS subscriptions with vibe-coded tools · How to use AI agents for errands, calls and shopping · How to use Cursor agents and automations · How to make 3D scenes and models with AI and Blender · How to use Claude Code skills and plugins · How to cut AI coding agent costs and token use · How to automate a small business with AI agents · How to compare AI models on the same prompt · How to build hardware projects with AI agents · How to make AI music videos and songs · How to use AI agents with Obsidian and your notes · How to build apps and games for your kids with AI · How to use ChatGPT for real projects and everyday tasks · How to make AI agents ask for approval before they act · How to build AI trading and investing agents · How to build AI agents that make and answer phone calls · How to plan meals and groceries with AI agents · How to use AI agents for fitness and health · How to undo, checkpoint and stop runaway coding agents · How to use AI agents for job hunting · How to automate social media posts with AI agents · How to build a smart home and voice assistant with AI agents · How to make money with AI agents · How to build a website with AI agents · How to build an iPhone or Android app with AI · How to automate email and your inbox with AI agents · How to use AI agents for Linux, servers and homelabs · How to build Telegram, Discord and WhatsApp bots with AI · How to research memecoins and crypto with AI agents
Five real AI use cases with setups, every morning. Free.
The Daily 5 will arrive in your inbox each morning. Unsubscribe any time.
Send the public link (post, video, repo or write-up). We credit you and link back.