Reported by sourceNew
Fill out repetitive web forms with Skyvern's vision-based browser agent
Skyvern drives a browser with an LLM and computer vision to complete forms, such as quote requests or contact forms, on sites it has not seen before.
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.
Showing 67 use cases
Planned, not doneNew
Auto-tag receipts and bills in Paperless-ngx with paperless-ai
paperless-ai suggests titles, tags, correspondents and dates for documents in a Paperless-ngx archive, using a local Ollama model or a cloud LLM, with manual review and undo.
Planned, not doneNew
Record and summarise meetings on your own machine with Meetily
Meetily records calls, transcribes them on the device with Whisper or Parakeet, and writes summaries with a local Ollama model or a cloud model you pick.
Planned, not doneNew
Build a formula-driven Excel model with the Claude xlsx skill
Install Anthropic's xlsx skill in Claude Code so the agent writes live formulas, recalculates the workbook with LibreOffice and checks it for formula errors.
Planned, not doneNew
Build a support chatbot that answers from your help docs with Dify
Turn help-centre pages into a Dify knowledge base, route questions with a classifier, answer from retrieved context and embed the bot on your website.
Planned, not doneNew
Find an open restaurant table with agentic AI Mode in Google Search
Google's AI Mode can check several reservation sites for tables that fit party size, time and cuisine, then send you to the booking page to finish yourself.
Reported by sourceNew
Build an app with Replit Agent while keeping production data out of reach
Replit Agent builds and browser-tests apps from a description. A widely reported 2025 incident, where it deleted a live database during a code freeze, shows why separate dev and prod data matters.
Reported by sourceNew
Compare products across open tabs with Claude in Chrome, then buy yourself
Claude in Chrome can read and compare what is open in your tabs and pull details into a table; Anthropic’s own red-team numbers explain why it asks before purchases and why you should finish checkout.
Reported by sourceNew
Explore and change a large codebase from the terminal with Gemini CLI
Gemini CLI is Google’s open-source terminal agent. Simon Willison found it strong on large codebases in 2025; in 2026 Google moved individual users to Antigravity CLI.
Reported by sourceNew
Find a product and buy it inside ChatGPT with Instant Checkout
OpenAI’s Instant Checkout lets you ask ChatGPT a shopping question, pick an item and confirm the order in chat; the open Agentic Commerce Protocol passes the order to the merchant.
Reported by sourceNew
Give Claude your Google Calendar and Gmail through a self-run MCP server
The open-source Google Workspace MCP server exposes Calendar, Gmail and other Workspace tools to Claude Desktop, Claude Code and other MCP clients, using your own OAuth client and optional read-only mode.
Reported by sourceNew
Hand coding tasks to Cursor cloud agents that open pull requests
Start Cursor agents from the editor, web, Slack or a GitHub comment; each works in its own cloud VM on a branch and returns a pull request with screenshots, videos and logs.
Reported by sourceNew
Let a self-hosted assistant file email and pre-draft replies with Inbox Zero
Inbox Zero works in the background on Gmail or Outlook: you write rules in plain English, and it files mail, drafts replies in your style, unsubscribes in bulk and briefs you before meetings.
Reported by sourceNew
Run parallel Devin sessions on repetitive migrations and test backlogs
Cognition reports customers giving Devin written migration and testing playbooks, then running many sessions in parallel; its own numbers show where Devin does well and where it needs a human.
Reported by sourceNew
Shop with an agentic browser without letting web pages give it orders
Perplexity pitches Comet for jobs like finding the same item with faster shipping. Brave showed a hidden comment could hijack it, and Simon Willison advises stopping agents at checkout.
Reported by sourceNew
Answer technical questions by letting async agents run experiments
Simon Willison sends research questions to cloud coding agents such as Claude Code for web and Codex Cloud, which write and run experiments in a dedicated repo and open a PR.
Reported by sourceNew
Let a coding agent run overnight ML training experiments
Point a coding agent at autoresearch so it edits a small GPT training script, runs short timed experiments and keeps what improves.
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
Build an on-call investigation agent from your own alert history
Goutham Veeramachaneni connected Claude Code to Grafana's gcx CLI, his code and runbooks, then trained its skill on two weeks of past pages for his services.
Reported by sourceNew
Extract invoice fields locally with a vision model on Ollama
Stephen Sebastian replaced a paid cloud OCR API with Gemma 4 E4B on Ollama to pull date, amount and description from contractor invoice photos on his laptop.
Reported by sourceNew
Trace a disk-filling production bug from core dumps with an agent
B12 CTO Adam Marcus used Claude Code to analyze gigabyte core dumps filling web server disks and traced them to an RSS endpoint reading an endless radio stream.
Reported by sourceNew
Build a cited Q&A knowledge base over your own documents
Self-host RAGFlow, upload PDFs, Office files and scans, and ask questions that come back with traceable source chunks.
Reported by sourceNew
Control smart-home devices with a local LLM voice assistant
Connect Home Assistant to a local Ollama model as its conversation agent so you can ask it to control exposed devices privately.
Reported by sourceNew
Parse scanned PDFs with tables into Markdown and JSON
Run PaddleOCR's PP-StructureV3 pipeline on scans to recover layout, tables, formulas and reading order as Markdown or JSON.