InternshipCounsellor

What the company appears to be: InternshipCounsellor is a self-reported tool for Canadian engineering students that helps them tailor resumes for co-op applications using AI. The system allows students to paste job descriptions, compare them with confirmed experience in a Master Profile, and generate tailored PDF resumes without fabricating experience.

What changed: The project description indicates this is a hackathon submission (Devpost entry for OpenAI 2026 hackathon). It was built as a proof-of-concept or prototype, not yet a commercial product. No evidence of revenue, customers, or traction exists beyond the author's own account.

Single most important open question: Is there any evidence that Canadian engineering students are using this tool, or that it has been tested with real users? The description states no revenue, customers, or adoption data exist — only the author’s own claims about its functionality and design decisions.

The description states that InternshipCounsellor is a "co-op application command center" for Canadian engineering students. It enables students to:

• Paste job descriptions from online postings
• Analyze requirements (skills, education, certifications, etc.)
• Compare these with confirmed experience in a Master Profile
• Generate tailored resumes based on real experience
• Export the resume as a PDF
• Track applications through various stages

The system uses AI to reorganize and highlight existing content but does not create false experience. It includes:

• Structured job requirement extraction
• Evidence-backed matching between student profile and job requirements
• Immutable resume versions
• Application tracking
• Private database access with authentication controls

It is built using Next.js, TypeScript, Supabase, React, OpenAI integrations, and other technologies.

Confidence: High — the description provides a detailed breakdown of functionality.

The author positions InternshipCounsellor as a solution to a specific problem: students submitting many generic applications without effectively showcasing their real experience. The core claim is that it helps students submit fewer, stronger, and more relevant applications while maintaining honesty.

Key positioning elements:

• Honesty-first approach: The system will not manufacture experience.
• Tailored application process: One workflow for job analysis → resume creation → tracking.
• Private and secure handling of sensitive data (resumes, employment history).
• Deterministic logic over AI-generated opinions.

The author also emphasizes that this is not just an AI demo but a working product with real workflows.

Confidence: Medium — claims are self-reported and lack external validation or traction data.

The description states that InternshipCounsellor targets Canadian engineering students seeking co-op positions. It is designed for those who:

• Are applying to multiple jobs
• Want to tailor their resumes manually but find it exhausting
• Have relevant experience they want to highlight, not invent
• Need a way to track applications in one place

There is no evidence of segmentation beyond this group or any indication of other potential users (e.g., career advisors, universities).

Confidence: Medium — the target customer is clearly defined but lacks supporting data.

The description does not state anything about pricing, monetization, or a business model. It only mentions:

• AI credits are used for operations
• A credit reservation system exists to avoid charging users when AI fails
• No mention of subscription plans, pay-per-use models, or revenue streams

Confidence: Low — no evidence of any commercial structure.

The author describes a technical architecture that includes:

• Next.js and TypeScript
• Supabase Postgres with Row Level Security
• Server-side OpenAI integrations
• Structured outputs validated against student data
• Deterministic logic for matching and tracking
• Credit reservation system to handle failed AI operations
• Strict authentication and ownership controls

Notable technical decisions:

• AI is constrained by confirmed evidence only
• No automatic applications or fabricated experience
• Immutable resume versions
• Private profiles and job descriptions
• Atomic credit handling

Confidence: High — the description gives a detailed account of engineering choices.

There is no evidence of traction, revenue, customers, or adoption. The project is described as a hackathon submission (Devpost entry for OpenAI 2026). It has no team size listed beyond "0", and there are no mentions of users, usage metrics, or product maturity.

The author notes that the system became a working product rather than just a demo, but this does not imply real-world use or market validation.

Confidence: Very low — absence of evidence for any traction or commercial activity.

The description does not mention competitors or similar tools. It does not describe how InternshipCounsellor compares to existing platforms for resume tailoring, job application tracking, or student career support services.

There is no indication of market analysis or competitive positioning beyond the author’s own claims about design constraints and honesty.

Confidence: Low — no evidence of competitive landscape or differentiation.

Several risks and red flags are evident from the self-reported description:

• No traction or user testing: The tool is described as a hackathon project with no real-world usage.
• Unproven value proposition: There’s no data on whether tailored resumes improve interview conversion.
• Limited scalability assumptions: The system uses server-side AI and deterministic logic, but it's unclear how this scales beyond one developer or small group of students.
• AI trust boundary design: While the author claims to have constrained AI behavior, there is no independent verification that these constraints are sufficient or effective in practice.
• No monetization path: No pricing model or revenue plan is evident.

Confidence: Medium — based on lack of evidence and self-reported assumptions.

1. Have you tested InternshipCounsellor with actual Canadian engineering students? What feedback did they give?
2. How many students have used the tool so far, if any?
3. Is there a plan to monetize this product? If yes, what is your pricing model?
4. What are the key assumptions behind your claim that evidence-backed resumes improve interview conversion?
5. Are you planning to integrate with university co-op programs or career services?
6. How do you intend to scale beyond a single developer’s development cycle?
7. What are the main technical challenges you expect in moving from prototype to production?