OpenAI 2026 hackathon

Beauty OS — Run a Salon by Asking

A safe AI operating system for salon owners: manage staff, schedules, services, clients, bookings, and growth through one agent.

Solo project by Mikhail Avdeev · 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 #2,893 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

What the company appears to be

Beauty OS is a self-reported salon operating system built with AI assistance, designed for salon owners who want to manage staff, schedules, services, clients, bookings, and growth through one interface — either visual or via an AI agent.

What changed

Between July 13–21, the team extended an existing product using Codex and GPT-5.6 during OpenAI Build Week. The extension added features like authentication, CRM integration, AI-assisted onboarding, a Copilot tool architecture with safe write previews, and analytics with AI Growth recommendations.

The single most important open question

Is there evidence of traction or adoption beyond the author’s own development work?

Note

This analysis is based entirely on the self-reported project description provided by the caller. No external verification, revenue data, customer names, or independent sources are available. All claims are stated by the author and not independently confirmed.

Back to contents

What The Product Actually Is

The description states that Beauty OS is an AI-powered salon operating system built by AI Beauty Bot. It offers:

  • A native workspace for managing:
    • Staff (specializations, availability, time blocks)
    • Services (categories, prices, durations, assignments)
    • Clients (phone-based deduplication, appointment history)
    • Calendar and appointments
    • Communication channels and notifications
    • Onboarding with AI-assisted spreadsheet import
    • Dashboards and AI Growth recommendations

It includes a “Owner Copilot” web widget that can be accessed from any screen. The agent supports both read and write operations, with all writes requiring confirmation after preview.

The system exposes 52 typed Copilot tools: 19 read and 33 write operations. Write actions are prepared as deterministic previews showing affected entities and warnings before execution.

Inference The product appears to be a hybrid CRM + AI assistant platform for small businesses in the salon industry, structured around an agent-based interface and domain-specific data models.

Back to contents

Positioning & Claim Evolution

The author states that existing CRMs make tasks possible but require manual effort and knowledge of where settings live. Generic chatbots answer questions but are not trusted operators of business operations.

They reframe the problem: “what if a salon owner could run the same operating system through both a complete visual interface and a safe AI agent?”

This positions Beauty OS as an AI-powered operational assistant for salon owners, combining CRM functionality with conversational AI to automate routine tasks while maintaining control over changes.

Claim

The product aims to simplify complex salon management by integrating AI into core workflows.

Inference This is a positioning shift from generic tools to a specialized AI agent that operates within a defined business domain (salon operations).

Back to contents

Target Customer & ICP

The description states the target audience is salon owners who currently use no external CRM.

It also implies a focus on smaller salons, as they are described as needing an “operating system” rather than full enterprise-grade tools.

Claim

Beauty OS targets salon owners without another CRM.

Inference The ICP likely includes small-to-medium-sized salons with limited tech infrastructure and a need for streamlined, AI-enhanced management.

Back to contents

Business Model & Pricing Evidence

Not evidenced.

The description does not mention pricing models, monetization strategies, or whether the product is sold directly to customers or through partners.

Finding

No evidence of business model or pricing structure provided.

Back to contents

Technical & Delivery Signals

The system uses:

  • Frontend: React, TypeScript, Vite, Tailwind CSS, shadcn/ui
  • Backend: Node.js, Hono, Zod, Drizzle ORM, PostgreSQL
  • AI tools: Codex, GPT-5.6

It implements:

  • A provider-neutral data-source contract allowing native and external CRM integration
  • Native salons use isolated beauty_os_* tables; integrations expose capabilities per domain
  • Copilot separates language understanding from execution
  • Tools are typed and deterministic (validation, conflict detection, previews)
  • Authentication, tenant isolation, multi-branch access, audit logging

Claim

The architecture is modular, secure, and scalable.

Inference The use of typed tools, deterministic validation, and separation of concerns suggests a mature engineering approach.

Back to contents

Traction & Maturity Signals

Not evidenced.

There is no mention of revenue, customers, user base, or usage metrics. The project was built during a hackathon and extended in a short timeframe.

Finding

No evidence of traction or adoption beyond the author’s own development work.

Back to contents

Competitive Context

Not evidenced.

The description does not reference competitors, market size, or competitive positioning beyond stating that existing CRMs are insufficient for this use case.

Finding

No evidence of competitive landscape or differentiation from other salon management tools.

Back to contents

Key Risks & Red Flags

  1. Unverified claims: All descriptions are self-reported and unverified.
  2. No traction or revenue: No evidence of customers, users, or monetization.
  3. Limited scope: The product is described as a prototype built in a hackathon environment.
  4. AI safety assumptions: Reliance on deterministic validation and confirmation for writes may be fragile at scale.
  5. Lack of clarity on long-term viability: No roadmap beyond next steps (e.g., role-based access, CRM adapters).

Inference The project is early-stage, likely a proof-of-concept or prototype, with no commercial traction yet.

Back to contents

Diligence Questions To Ask The Founders

  1. What is the current state of the product outside of the hackathon build?
  2. Are there any existing users or pilot programs?
  3. How does the AI agent handle ambiguous inputs or edge cases?
  4. What are the plans for monetization and go-to-market strategy?
  5. Is there a plan to integrate with major CRM providers beyond the current native support?
  6. How is data privacy and compliance handled, especially around client information?

Back to contents

Investment/Partnership Verdict

Not evidenced.

There is no evidence of revenue, customers, or financial performance to assess investment potential or partnership value.

Finding

No basis for evaluating whether this project is ready for investment or strategic partnership. The product appears to be a prototype with strong technical foundations but no demonstrated commercial traction or market validation.

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.