Joblit: the job search that will not lie on your CV

What the company appears to be: Joblit is a self-reported AI-powered job search platform designed to filter out roles that are inaccessible to users based on experience, work rights, and title requirements, while also tailoring CVs without inventing skills or experiences. It claims to run locally on user machines using Hermes-hosted GPT 5.6, with no data sent externally.

What changed: The author describes a personal frustration with LinkedIn’s job search process — particularly the delay in posting visibility and the prevalence of misleading job descriptions. They built Joblit as an alternative that filters early, avoids false claims in CVs, and operates locally to preserve privacy.

Single most important open question: Is there evidence of actual user adoption or traction beyond the author's own use case? The description provides no data on users, revenue, or product-market fit beyond a single developer’s personal project.

Note: This analysis is based entirely on self-reported information from the project description. No third-party verification, archived data, or independent sources are available.

The description states that Joblit is:

• A job search tool that filters roles before they reach the user.
• A CV tailoring tool that refuses to lie by ensuring every claim traces back to real profile evidence.
• A local application that runs on the user’s machine, using Hermes-hosted GPT 5.6.
• A Chrome extension that auto-fills forms and tracks applications.
• Available in English and Chinese with separate resume templates.

It is built as a SaaS platform but claims to operate entirely locally, with no external data transmission.

Inference: The product appears to be a prototype or personal tool rather than a commercial offering. There is no evidence of a marketplace, customer base, or monetization strategy beyond the author's own use case.

The author positions Joblit as:

• A solution to the inefficiencies of LinkedIn’s job search.
• A tool that prevents users from wasting time on roles they cannot apply to.
• A CV generator that avoids falsifying experience or skills.
• A privacy-preserving alternative to cloud-based AI tools.

It evolves from a personal frustration into a tool with broader implications for job seekers and AI use in recruitment.

Claim: The author claims Joblit is “the job search that will not lie on your CV.” This is a positioning statement, not evidence of traction or adoption.

The description states:

• The primary user is a new grad in Australia.
• The tool is built for people who are frustrated with LinkedIn’s job search and AI-generated CVs.
• It supports English and Chinese speakers.

No explicit segmentation beyond this is provided. The author does not describe how they would scale or target other personas (e.g., experienced professionals, international users, etc.).

Inference: The ICP appears to be a single user — the author — with no evidence of a broader target market or customer acquisition strategy.

The description states:

• Joblit is described as a SaaS platform.
• It runs locally on the user’s machine, suggesting no recurring revenue model at this stage.
• There is no mention of pricing, subscriptions, or monetization.

Not evidenced: No business model or pricing information is provided beyond the self-reported claim that it is a SaaS product.

The description states:

• Built with Next.js, React, Postgres, Prisma, NextAuth.
• Uses Python JobSpy worker on GitHub Actions for LinkedIn intake.
• Integrates Hermes-hosted GPT 5.6 via loopback.
• Chrome extension auto-fills forms and tracks applications.
• Supports English and Chinese with separate templates.
• Includes CI/CD, linting, dead code checks, and 1700+ tests.

Inference: The technical stack suggests a developer-focused, local-first product. However, there is no evidence of scalability or production deployment beyond the author’s own machine.

The description states:

• It is a finished product, not a demo.
• Contains 28 tables, 68 API routes, and supports multi-language.
• Has auth, rate limiting, migrations, CI/CD, and extensive testing.
• The author built it to professional code review standards.

However, there is no evidence of:

• User adoption or feedback.
• Revenue or monetization.
• Customer base or usage metrics.
• Product-market fit or retention.

Not evidenced: No traction or maturity indicators beyond the author’s own development effort.

The description states:

• Joblit is a response to LinkedIn’s job search limitations.
• It aims to improve upon AI-generated CVs that “invent” skills or experiences.
• It competes with tools that auto-fill forms and tailor resumes.

No mention of direct competitors, market size, or competitive positioning beyond the author's own frustration.

Inference: The competitive landscape is not described. Joblit appears to be a niche tool for job seekers, but no evidence of existing competition or market dynamics is provided.

• Single-user product: No evidence of broader adoption or scalability.
• Local-first approach: May limit user experience and scalability.
• No revenue model: The SaaS claim lacks monetization strategy.
• Unverified claims: The author’s own account is unverified, with no third-party validation.
• Limited scope: The tool appears to be a personal solution rather than a scalable platform.

Inference: The product may not be ready for commercial use or market adoption without further development and evidence of traction.

1. What is the actual user base beyond yourself?
2. How do you plan to monetize this tool if it’s currently a personal project?
3. What are the technical limitations of running AI locally at scale?
4. Have you tested the filtering logic with real-world job data?
5. Are there any plans for integrating with more ATS platforms or expanding beyond LinkedIn and company boards?
6. How do you intend to handle edge cases in skill matching or role filtering?