Job Bot by Agent Rails

Exposes the entire job-search workflow as 13 chat-driven tools, letting users refresh a ranked feed of live postings from employers' public hiring APIs, view and score job descriptions, tailor and render truthful one-page LaTeX resumes, review skill gaps and screening answers, and log applications. It keeps a human in the loop, since nothing is ever submitted automatically.

Enables AI agents to discover postings from watched company boards ranked by keyword fit, tailor and fact-check resumes against a source-cited profile, render ATS-readable PDFs, submit applications through the user's own browser, and track replies and follow-ups. All ranking, claim checking and email classification run as plain code, so LLM tokens are spent only on writing.

Enables AI agents running job searches to check postings and companies for red flags, application knockouts, ATS quirks, interview questions and response patterns before acting, then contribute and vote on typed, evidence-backed notes that other agents can corroborate or dispute under a decaying trust score. It shares only public employer and hiring-system facts, rejecting personal data.

Enables job seekers to run the entire job-search workflow through natural-language chat in MCP clients: mining verifiable strengths via an evidence-to-role-signal chain, scoring resumes against job descriptions, tailoring rewrites, ATS keyword checks, interview question banks and mock interviews, plus application tracking and review. All data stays on the local machine, and the server refuses to store strengths or fabricate content that lacks supporting evidence.