Using the Agent
Task-shaped guides: a concrete thing you want done, and how an AI agent with a real browser actually does it. Worked examples, with the real transcripts and the files they produced, live in the repository's articles/ folder; the pages here are the reading companion - what works, what breaks, and what to expect before you spend model tokens finding out.
- Getting an AI agent to fill out forms
- Which model to use with AIHawk
- Browser problem or model problem?
- Running AIHawk's browser from Claude Code
- Extracting data to a CSV with an AI agent
- Monitoring a page for changes with an AI agent
- Running AIHawk's browser from Claude Desktop
- Running AIHawk's browser from Cursor
- Using an AI agent to hunt for apartments
- Getting website data into Google Sheets with an AI agent
- Using an AI agent to download invoices from portals
- AI agents for web research
- Using an AI agent to test your own website
- Running AIHawk's browser from Cline
- Posting to social media with an AI agent
- Posting to Facebook with an AI agent
- Posting to Instagram with an AI agent
- Posting to X with an AI agent
- Automating LinkedIn posts: read this first
- Appointment bots: what they are and what an agent can legitimately do
- The MCP server: config blocks, settings, tools
- How the tools are shaped, and why
- Playwright MCP vs the Playwright CLI
- Playwright MCP: browser is already in use
- Playwright MCP best practices
- Playwright MCP with a proxy
- A browser MCP server in GitHub Copilot
- Using a browser MCP server for web scraping
- Which LLM for browser automation
- How to build a browser agent
- Getting an AI agent to log into a website