AIAny
AI Agent2026
Icon for item

AI Job Search

Evaluates job postings and produces tailored CVs, cover letters, and interview prep using a Claude Code-driven agent workflow. Distinguishes itself with a drafter–reviewer loop, mandatory PDF compilation and ATS text-layer verification, plus extensible portal scrapers and LaTeX templates.

Introduction

Why this matters Most automated resume tools stop at text generation; this workflow treats the PDF as the product. It automates job matching, drafts tailored LaTeX CVs and one-page cover letters, runs a separate reviewer agent, compiles and inspects PDFs, and verifies the CV text layer for ATS compatibility—reducing the common gap between “looks right” and “parses right.”

What Sets It Apart
  • Drafter–reviewer pipeline: one agent drafts tailored documents and a fresh reviewer agent researches the company and critiques framing and keywords, so drafts are iteratively improved rather than accepted in a single pass.
  • PDF-first verification: the system compiles CVs/letters and programmatically fixes layout issues (orphans, font fallbacks) until page limits and visual constraints are met, so the delivered PDFs match recruiter expectations.
  • ATS text-layer checks: extracts the PDF text layer to confirm contact info and keyword visibility from an ATS perspective, preventing subtle LaTeX extraction failures that break automated parsers.
  • Extensible search skills and templates: ships CLI skills for Danish portals and a country-agnostic LinkedIn skill; supports adding portal scrapers and user LaTeX templates via built-in commands.
Who It's For and Trade-offs

Great fit if you maintain a detailed documents/LinkedIn/CV corpus and want high-assurance, tailored applications at scale—especially users who need both human-readable PDFs and machine-parseable output. Not ideal if you lack any source documents, cannot run Claude Code or LaTeX locally, or need a simple web UI; the workflow assumes command-line use, Claude Code access, and a LaTeX toolchain (lualatex/xelatex).

Information

  • Websitegithub.com
  • AuthorsMads Lorentzen
  • Published date2026/03/18

Categories

More Items

Hugging Face
AI Model2026

Combines Korean-English language and image understanding with screenshot-driven browser control in one model. It prioritizes retaining general LLM and VLM capabilities rather than optimizing solely for web tasks.

GitHub
AI Agent2026

Coordinates multiple coding agents in one workspace: an assistant delegates tasks, tracks their progress, and reports back. Runs locally and uses the model plans or keys you already have.

Hugging Face
AI Model2026

Combines scientific data understanding with search, coding, and tool use for multi-step research. It checks intermediate results and visual feedback to revise its actions, and accepts more than ten scientific data types.