Sign InOpen Brain
GitHubGitHub RepoNeeds Review

MadsLorentzen/ai-job-search

This Claude Code framework is a concrete agent-harness pattern: structured source files, specialized commands, a drafter-reviewer loop, compilation checks, and explicit human approval boundaries.

GitHub
Open Source Open MarkdownOpen JSON
Source Summary

The local-first framework covers profiling, job discovery, fit ranking, tailored applications, and interview preparation. Its core pipeline uses a **second reviewer agent** and a **PDF compile loop**; the author reports 69 applications, 20 first interviews, and one contract.

Practical Implication

Study it as a reusable harness pattern: keep source data in files, split work into named skills, give agents explicit evaluation criteria, and verify generated artifacts with deterministic tools before presenting them. Human approval remains in the tracking and messaging flows.

Agent-Ready Context
The local-first framework covers profiling, job discovery, fit ranking, tailored applications, and interview preparation. Its core pipeline uses a **second reviewer agent** and a **PDF compile loop**; the author reports 69 applications, 20 first interviews, and one contract.

Study it as a reusable harness pattern: keep source data in files, split work into named skills, give agents explicit evaluation criteria, and verify generated artifacts with deterministic tools before presenting them. Human approval remains in the tracking and messaging flows.

Its portal integrations are mainly Danish, and instruction-level prompt-injection defenses are **not a sandbox**. A public fork can expose tracked personal data, so personal use should start from a private repository with this project configured as upstream.
Connected Context · Feed7 Judgment

This turns familiar harness patterns into an end-to-end, consequential personal workflow with reported funnel outcomes: file-backed state, named skills, a second reviewer, deterministic PDF checks, and human approval. It reinforces structured delegation without validating general hiring effectiveness; Danish integrations, prompt-injection exposure, and the risk of publishing personal data materially narrow reuse.

santifer/career-opsBoth apply coding-agent harnesses to job searching, but this adds a second-reviewer and PDF-compilation loop plus reported application-to-interview outcomes, while retaining human control over consequential actions.How AI Agents Let GTM Teams Scale — Justin Joyce, CloudflareIt transfers the same separation of domain knowledge, drafting, and verification from GTM work into applications, with files and deterministic artifact checks making the pattern concrete.FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem GenerationIts PDF compile-and-retry loop parallels the generate, compile, verify, and retry structure used for formally checked synthetic geometry artifacts.Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard DocumentsThe second reviewer reinforces evidence that specialized, staged review can outperform one generic pass, while neither source establishes broad cross-domain reliability.
Context Map
agentresearchdata#harness-engineering#multi-agent#skills
Uncertainty
Its portal integrations are mainly Danish, and instruction-level prompt-injection defenses are **not a sandbox**. A public fork can expose tracked personal data, so personal use should start from a private repository with this project configured as upstream.