740+ job offers. That's the outcome one developer reported after building an AI-powered job search system with Claude Code and running it through a search that ended with an actual job. The code is now public on GitHub.
The system automates the mechanical parts of job hunting: finding and filtering listings, scoring them against a personal profile, and generating tailored application materials. It runs as a multi-agent pipeline - multiple AI processes working in sequence - coordinated through Claude Code, Anthropic's AI coding assistant.
The 740+ figure needs context. At that scale, "offers" almost certainly counts positive signals across the funnel: recruiter replies, screening calls, interview requests, rather than 740 formal employment contracts. The relevant proof point is simpler: the developer ran the system, went through the process, and got hired.
Running this requires a Claude API key and comfort with Claude Code. There's no hosted app, no point-and-click interface. Setup involves configuring the system around your specific job targets and background - this is developer-level effort.
For developers willing to put in that setup time, the open-sourced code is a working example of multi-agent job search automation with a documented real-world outcome. Most AI job search tools are generic resume polishers or scraper utilities without real intelligence behind the matching. A functioning pipeline built by someone who proved it works is a more honest starting point than most of what's in this space.