Ask Momo

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 treated as stated by the author and not proven.

The description states that Ask Momo is a Next.js and TypeScript web application hosted on Vercel, using Supabase for authentication and private saved-claim persistence. It integrates with OpenAI's API via GPT-5.6 to assist in organizing facts, identifying airline claims, and suggesting neutral wording.

Key features include:

• A no-account starting flow
• Ability to describe events or paste an airline reply
• Review of confirmed vs missing facts
• Source-backed UK/EU disruption assessment with official source cards
• Rejection Dissector tool that identifies airline claims, quoted wording, missing explanations, and suggests a neutral next question
• Editable draft message before sending

The product is described as not providing legal advice, nor promising compensation. It uses a deterministic rules engine to control scope, fact gates, uncertainty, and official sources, while GPT-5.6 is used only for constrained tasks such as organizing facts or drafting wording.

Inference: The product appears to be a prototype built in a short timeframe (hackathon), with limited commercial functionality beyond its initial use case.

The author positions Ask Momo as a calm, friendly flight-disruption advocate that helps travellers understand vague airline replies and write better next messages without AI inventing legal answers.

It is described as:

• Not a lawyer or legal advisor
• Not promising compensation
• Focused on helping users ask the right questions
• Designed to avoid common failure modes like sounding confident while inventing legal conclusions

The project evolved from a personal experience into a tool for others, with an emphasis on trust-building through transparency and bounded AI use.

Claim: The author claims this is not a replacement for legal advice or a compensation provider.

Inference: The positioning reflects an attempt to differentiate from overly aggressive or misleading tools in the market.

The target customer is described as:

• Travellers who have experienced airline disruptions, particularly those involving unclear responses, inconsistent compensation offers, or lack of support.
• Individuals seeking a structured way to respond to airlines without emotional outbursts or unsupported claims.
• Users who may be stressed during travel disruptions and need calm guidance.

The ICP is not explicitly defined beyond this general category. The product supports both:

• No-account starting flows
• Later account creation for saving claims across devices

Inference: The target audience seems to be primarily UK/EU-based travellers, though the author mentions cautious international information where verified sources are available.

There is no evidence of pricing, revenue models, or monetization strategies in the description. The author states that Momo:

• Does not promise compensation
• Is not a lawyer or legal advisor
• Does not send claims for users
• Is meant to be a backbone for a future company

The author mentions potential partnerships with:

• Insurance companies
• Employer benefits providers
• Law/legal partners

They also suggest monetization via these channels.

Claim: The author believes Momo can connect with insurance or legal partners for revenue.

Inference: No actual business model or pricing data is provided; this remains speculative based on stated intentions.

The product is built using:

• Next.js
• TypeScript
• React
• Supabase (for authentication and persistence)
• Tailwind CSS
• Vercel (hosting)

It uses GPT-5.6 in a bounded manner, with:

• Schema and rule validation
• Deterministic decision receipt and official rule cards
• Input validation, size limits, privacy-preserving rate limits, and strict model-output validation

The author mentions using Codex to accelerate development and built-in automated test suites covering various edge cases.

Inference: The technical stack suggests a modern, scalable architecture suitable for production, but no evidence of scaling or deployment beyond the hackathon prototype.

There is no evidence of:

• Revenue
• Customers
• User adoption
• Product usage metrics
• Any form of traction beyond the author’s own experience and stated intention to build a company around it

The product is described as a hackathon submission, and the author notes that they will use it themselves and give it to friends.

Claim: The author intends to turn this into a company.

Inference: No traction or growth data are available; the project remains in early-stage prototype form.

The description does not mention any direct competitors. However, the concept of helping travellers navigate airline disruptions and claim compensation is not new. Other tools in this space might include:

• Travel insurance platforms
• Legal aid services for flight delays
• Consumer advocacy groups
• AI-powered travel assistants (though none are named)

Inference: The competitive landscape likely includes existing solutions, but no comparison or differentiation from them is made.

Key risks and red flags include:

• No commercial traction — the project is described as a hackathon submission with no evidence of real-world usage.
• Unverified claims about AI safety — while the author describes bounded use of GPT-5.6, there’s no independent verification of how well this is enforced.
• Lack of business model clarity — monetization plans are speculative and not backed by data or prior execution.
• Single-founder team — only one member listed (Alay Merchant), which may limit scalability.
• No external validation — the entire description is self-reported, with no third-party confirmation.

Inference: The lack of traction, unclear monetization, and single-person development raise concerns about viability and scalability.

1. What specific evidence do you have that users are actively using this tool beyond your personal use?
2. How do you plan to scale the product beyond a single developer’s effort?
3. Have you validated demand for this service with potential partners (insurance, legal, etc.)?
4. Can you explain how the deterministic rules engine handles edge cases not anticipated during development?
5. What are the actual costs and time investments required to move from prototype to production-ready version?
6. How do you intend to ensure data privacy and security compliance at scale?