OpenAI 2026 hackathon

ApplySmart

AI career assistant that finds ,do recruiter outreach and applies for Jobs within seconds on your behalf

Solo project by Manasvi Dawane · 0 likes · 0 comments

Archive position — measured, not model output

0 likes on Devpost

2,264 of the 7,856 archived projects have more likes, and 5,592 share exactly 0 — so this project's #2,684 place in the like-ranked listing is a tie-break inside that group, not a ranking.

Projects (log scale)

1
10
100
1k
10k
05,592
11,758
2285
3–4132
5–975
10+14

Likes on Devpost. ▲ marks this project's group.

Show the figures
LikesProjectsShare of archive
05,59271.2%
11,75822.4%
22853.6%
3–41321.7%
5–9751.0%
10+140.2%
Devpost like counts for all 7,856 archived projects, captured when this archive was built.

Executive Summary

Company: ApplySmart

Self-reported basis: The description is entirely self-reported and unverified, based on a Devpost submission for the OpenAI 2026 hackathon. No external verification or historical data is available.

What it appears to be: A prototype AI-powered tool that automates job applications by finding jobs, personalizing content, filling forms, and sending outreach messages — all with human approval.

What changed: The project was submitted as a hackathon entry; no evidence of product-market fit, traction, or commercialization is provided.

Single most important open question: Is there any evidence of user adoption, revenue, or customer feedback beyond the author’s own claims?

Back to contents

What The Product Actually Is

The description states that ApplySmart is an AI career assistant that finds jobs, personalizes resumes and cover letters, fills application forms, drafts recruiter emails, and automates submissions with human approval when needed. It uses LLMs, browser automation, web search, and persistent memory to function as an “AI Application Copilot” on job portals.

Evidence:

  • The author states: “ApplySmart finds relevant jobs, personalizes resumes and cover letters, fills application forms, drafts recruiter emails, and automates submissions with human approval when needed.”
  • The author states: “We combined LLMs, browser automation, web search, and a persistent career memory to create an AI Application Copilot that works directly on job portals.”

Inference:

  • The tool appears to be a browser-based automation system integrated with AI models for personalization and form-filling.
  • It is described as working “directly on job portals,” suggesting integration with platforms like LinkedIn, Indeed, or others.

Back to contents

Positioning & Claim Evolution

The author positions ApplySmart as an AI assistant that goes beyond simple resume writing to actually complete job applications autonomously — while keeping users in control through human approval. The project is described as a “career copilot” and an “AI Application Copilot.”

Evidence:

  • The author states: “We wanted to build an AI that doesn't just write resumes but actually completes applications while keeping users in control.”
  • The author states: “Building an end-to-end AI that goes beyond chat by actually completing job applications and reducing a lengthy process to just a few clicks.”

Inference:

  • The positioning is focused on automation of repetitive tasks in job searching, with emphasis on user agency.
  • It implies a shift from generic AI tools to task-specific automation within the job market.

Back to contents

Target Customer & ICP

The description does not clearly define the target customer or ideal customer profile (ICP). The author focuses on the general problem of time-consuming job applications but does not specify who uses this tool, what their role is, or how they are segmented.

Evidence:

  • The author states: “Applying to jobs is repetitive, time-consuming, and frustrating.”
  • No explicit customer segment or persona is defined.

Inference:

  • Likely aimed at job seekers — particularly those applying to many positions.
  • Possibly relevant for early-career professionals or those in competitive markets.

Back to contents

Business Model & Pricing Evidence

There is no evidence of a business model or pricing structure. The description does not mention monetization, subscriptions, or any revenue-generating mechanism.

Evidence:

  • No mention of pricing, monetization, or business model.

Inference:

  • If commercialized, it might be a SaaS product with usage-based or subscription pricing — but this is speculative.

Back to contents

Technical & Delivery Signals

The project was built using a stack including LLMs (OpenAI, LangGraph), browser automation (Playwright), AI agents, and web scraping tools. It uses Next.js, React, FastAPI, PostgreSQL, Supabase, and Redis.

Evidence:

  • The author states: “We built it with agents, ai, api, clerk, css, fastapi, gpt, html, javascript, langgraph, next.js, node.js, ocr, openai, playwright, postgresql, python, react, redis, rest, supabase, tailwind, typescript, vector, vercel.”
  • The author states: “We combined LLMs, browser automation, web search, and a persistent career memory.”

Inference:

  • The tool is built with modern AI and automation stack.
  • It integrates with job portals using browser automation.

Back to contents

Traction & Maturity Signals

There is no evidence of traction or maturity beyond the hackathon submission. No customers, revenue, usage data, or product adoption are mentioned.

Evidence:

  • The project was submitted to a hackathon (OpenAI 2026).
  • No mention of users, customers, or product usage.

Inference:

  • Likely in early prototype stage.
  • No evidence of real-world testing or user feedback.

Back to contents

Competitive Context

The description does not provide any information about competitors or the competitive landscape. It is unclear whether similar tools exist or how ApplySmart differentiates.

Evidence:

  • No mention of competitors, market analysis, or differentiation.

Inference:

  • The job application automation space likely includes tools like Jobscan, Resume.io, and various AI resume builders — but no evidence of awareness or positioning against them is provided.

Back to contents

Key Risks & Red Flags

  • No traction or revenue: The project is a hackathon submission with no evidence of adoption or monetization.
  • Technical complexity risks: Browser automation and LLM integration are complex; reliability issues may be common.
  • Ethical and legal concerns: Automating job applications may raise ethical questions around authenticity, platform rules, or AI misuse.
  • Unproven market need: The author describes a problem but does not validate demand or user feedback.

Back to contents

Diligence Questions To Ask The Founders

  1. What specific job portals does ApplySmart support, and how does it handle platform-specific UIs?
  2. How does the tool ensure compliance with job portal terms of service?
  3. Have you tested the tool with real users? What feedback did you get?
  4. What is your plan for monetization or scaling beyond a hackathon prototype?
  5. How do you manage data privacy and user consent in an AI-driven application process?

Back to contents

Investment/Partnership Verdict

Not evidenced: No evidence of revenue, customers, traction, or commercial viability is provided. The project is described as a hackathon submission with no indication of product-market fit or business development.

Confidence level: Low. The description is self-reported and unverified, and lacks any data on adoption, monetization, or competitive positioning.

Conclusion: ApplySmart appears to be an early-stage prototype addressing a common pain point in job searching. It has not demonstrated commercial viability or traction. Further diligence would require evidence of user testing, product-market fit, or revenue.

Back to contents

Source

Submitted to the OpenAI 2026 hackathon on Devpost. Project home on DevPost.

The analysis above was generated by a language model from the project's own one-line description. It is not independent research and contains no verified traction, revenue or customer data.