Show HN: AI agent that runs real browser workflows
Posted by heavymemory 3 hours ago
I’ve been experimenting with letting an AI agent execute full workflows in a browser.
In this demo I gave it my CV and asked it to find matching jobs. It scans my inbox, opens the listings, extracts the details and builds a Google Sheet automatically.
Comments
Comment by fidorka 1 hour ago
I've been building MemoryLane (https://github.com/deusXmachina-dev/memorylane) which comes at this from the other side - it records screen activity, spots repeated patterns with AI, and then tells you "hey you keep doing this, want to automate it?" Works as an MCP plugin for Claude/Cursor.
Feels like pattern detection (finding what to automate) + browser agents like yours (actually doing the automation) is the right combo. Are you thinking about the discovery side at all, or mostly focused on execution?
Comment by heavymemory 55 minutes ago
Comment by hkonte 2 hours ago
Structuring the task prompt into named blocks (objective, constraints, expected output format per step) before the workflow starts makes each step much more reliable. The agent has less to infer.
Built github.com/Nyrok/flompt to help with this, a visual builder that decomposes instructions into semantic blocks and compiles to Claude-optimized XML. Useful for defining the "task shape" before handing it to an agent.
Comment by heavymemory 2 hours ago
So the model isn’t carrying the whole instruction chain across multiple steps, it’s just solving the current task. Similar pattern to what tools like Codex CLI or Claude Code do.
Comment by abraxas 3 hours ago
Comment by heavymemory 3 hours ago
Just need to see if people find this version useful