Reported by sourceNew
Crawl a docs site into clean Markdown for a RAG index
Use Firecrawl to map and crawl a website, returning each page as Markdown or structured JSON ready to chunk and embed.
67 use cases · 61 agents
AI Use Cases
Real jobs people get done with AI agents, each tied to its original source, an honest outcome label, a prompt you can edit, and the GitHub repositories involved.
Start here
Reported by sourceNew
Run an open-weight model locally and call it from your code
Install Ollama, pull an open model and call it through the local REST API so prompts stay on your machine.
Reported by sourceNew
Review pull requests automatically with Claude in GitHub Actions
Install the Claude Code GitHub Action so Claude reviews each pull request with inline comments and responds to @claude requests.
Reported by sourceNew
Port a Python library to JavaScript with a coding agent
Simon Willison had Codex CLI translate the JustHTML parser into a dependency-free JavaScript library, steering it with about eight prompts over one afternoon.
Showing 67 use cases
Planned, not doneNew
Get automatic briefings before external calls with Lindy Meeting Prep
Lindy’s Meeting Prep routine sends a briefing before each meeting, or as a daily digest, with the attendees, their job titles and companies, and summaries of earlier meetings, by email or text.
Planned, not doneNew
Qualify inbound sales emails and draft replies for review with Make AI Agents
Make’s help center walks through an agent that reads lead emails, researches the sender’s company, scores the lead, checks your calendar and leaves a draft reply in Gmail with a Slack link for you to review.
Planned, not doneNew
Hand off research and document tasks to the Dispatch agent in Claude Cowork
Anthropic’s Cowork docs describe Dispatch, a background agent in Claude Desktop that splits one request into child tasks, runs each as its own session and forwards permission prompts to you, even from your phone.
Reported by sourceNew
Get a new OCR model running on unfamiliar GPU hardware with Claude Code in a sandbox
Simon Willison gave Claude Code full permissions inside a Docker container on an NVIDIA Spark and had it get DeepSeek-OCR working; it took four prompts and under 40 minutes, with one nudge from him.
Planned, not doneNew
Delegate errands to Meta’s Muse, with approval before it sends or buys
Meta’s Muse runs in its own secure cloud VM, takes requests in WhatsApp or the Muse app, and asks before sending email or buying; a separate Sentinel agent must approve anything it sends to the internet.
Planned, not doneNew
Hand CRM updates and follow-up drafts to Grok Bot agents with approval steps
Grok Bot launched in beta in August 2026: always-on agents with their own cloud computer that sign in to your apps, learn routines by watching you, and come back when something needs your approval.
Planned, not doneNew
Let Microsoft Scout prepare meetings and sort out calendar conflicts in Microsoft 365
Microsoft announced Scout at Build 2026: an always-on personal work agent for Frontier customers, built on the open-source OpenClaw and on Work IQ, that handles meeting prep, scheduling conflicts and routine tasks.
Planned, not doneNew
Research new business leads and brief your sales team with Zapier Agents
Zapier’s guide shows an agent that starts when a lead arrives, looks up the company on the web, adds the details to your CRM and drafts outreach, with approval steps you add before anything is sent or changed.
Reported by sourceNew
Build a formula-based analysis workbook with Agent Mode in Excel
Agent Mode in Excel plans formulas, sheets and charts from a prompt, checks and fixes its own results, and reports its validation steps; Microsoft reports 57.2% accuracy on SpreadsheetBench in its own evaluation.
Reported by sourceNew
Apply the context engineering lessons from Manus to a long-running agent loop
The Manus team describes the context rules it settled on after rebuilding its agent framework four times: keep the prompt prefix cacheable, mask tools instead of removing them, and use files as memory.
Reported by sourceNew
Hunt for variants of fixed bugs with an LLM agent, as Google's Big Sleep did in SQLite
Google's Big Sleep agent started from recent SQLite fixes, looked for related unfixed bugs and found an exploitable stack buffer underflow before it reached an official release.
Planned, not doneNew
Turn public competitor pages into a structured market scan with Crawl4AI
Crawl4AI crawls pages into clean Markdown and extracts fields such as product names and prices with CSS or XPath schemas or an LLM, giving an agent tidy input for a market or competitor comparison.
Planned, not doneNew
Prototype agent checkout with signed user mandates using Google's AP2
AP2 is an open protocol from Google for payments made by agents: the user signs an intent mandate and a cart mandate, giving merchants and payment providers an audit trail of what the user approved.
Planned, not doneNew
Import recipes and plan the week's meals in self-hosted Mealie with an AI provider
Mealie is a self-hosted recipe manager and meal planner; with an OpenAI-compatible provider it can turn web pages, pasted text or photos into recipes, parse ingredients and suggest tags.
Reported by sourceNew
Program a robot dog with an AI assistant: Anthropic's Project Fetch experiment
Anthropic split eight staff without robotics experience into two teams to program a quadruped robot to fetch a ball; the team using Claude finished more tasks and, on shared tasks, took about half the time.
Planned, not doneNew
Try a desktop-operating agent safely in Anthropic's computer use demo container
Anthropic's computer-use-demo runs Claude inside a Docker desktop that you watch in the browser, with a chat panel, so you can test screen, mouse and keyboard automation away from your own machine.
Planned, not doneNew
Run long research tasks with sub-agents in DeerFlow
DeerFlow 2.0 is an open-source agent harness from ByteDance that plans a task, hands parts to sub-agents and works in a sandbox with memory, skills and search tools, using any OpenAI-compatible model.
Planned, not doneNew
Run coding agents from one self-hosted control centre with OpenHands
OpenHands Agent Canvas runs the OpenHands agent, or Claude Code, Codex, Gemini CLI and other ACP agents, on your machine or in Docker sandboxes, and can trigger them from schedules or webhooks.
Planned, not doneNew
Build a voice agent that answers and places phone calls with Pipecat
Pipecat is an open-source Python framework for real-time voice agents; its telephony support lets a bot take inbound calls or dial out through providers such as Twilio and Telnyx.
Planned, not doneNew
Watch competitor pricing and product pages with changedetection.io
changedetection.io checks chosen parts of web pages on a schedule, tracks prices and restocks, and can use an LLM to summarise changes or ignore ones that do not matter.
Reported by sourceNew
Evolve faster algorithms with AlphaEvolve and automated evaluators
Google DeepMind's AlphaEvolve pairs Gemini models with automatic scoring to evolve code, and reports gains in data-centre scheduling, AI kernels and open maths problems.
Reported by sourceNew
Generate long maths explainer videos with an agent that writes Manim code
TheoremExplainAgent plans scenes, writes Manim Community animation code and adds narration to produce theorem explanation videos longer than five minutes.
Planned, not doneNew
Build and debug a Godot game with an agent through godot-mcp
godot-mcp lets an MCP client launch the Godot editor, run a project, read its debug output and create scenes, so the agent can check whether its game code works.
Planned, not doneNew
Let an agent decompile and annotate a binary in Ghidra through GhidraMCP
GhidraMCP exposes Ghidra's decompiler and renaming tools over MCP, so an agent such as Claude Code can list functions, read decompiled code and propose clearer names.