Lot Foundry

Analysis basis

This report is based entirely on the self-reported description provided by the project author. No external verification, traction data, customer names, or financials are available. All claims are treated as stated by the author and not independently confirmed.

The description states that LotFoundry allows users to input an address and then walks them through five steps:

1. Find – shows what the lot looks like on paper.
2. Earn – provides rent, income, and payback estimates.
3. Shape – lets users drag an ADU around their lot in 3D with real-time setback updates.
4. Check – includes zoning and permit questions.
5. Act – generates a shareable feasibility report.

It also supports:

• Saving runs
• AI-written summaries of parcel/permit situations
• Uploading house photos for style-matched ADU concepts (opt-in feature)
• Deterministic math engine that does not change numbers based on AI

Inference The product appears to be a web/mobile application with 3D visualization and AI-assisted property planning. It is built using Next.js, React, Firebase, Three.js, and integrates with OpenAI models.

The author positions LotFoundry as a tool that answers the question: “Is this even worth pursuing on my lot?” The tagline emphasizes AI-powered insights from property data for homeowners planning ADUs.

Key claims:

• It pulls property data and provides ADU concepts, feasibility insights, zoning checks, and ROI estimates.
• It helps homeowners plan and build with confidence.
• It uses OpenAI models to explain numbers without changing them.
• It separates “recorded fact,” “estimate,” and “AI-generated” information for clarity.

Inference The positioning is focused on simplifying complex ADU planning for homeowners, especially those unfamiliar with zoning or construction. The emphasis on trust and transparency in data presentation suggests a focus on user confidence over raw functionality.

The description states that LotFoundry targets homeowners who are considering building an ADU — a group seeking extra rental income, family space, or added property value.

It also mentions:

• Users who want to know if it's worth pursuing their lot.
• Homeowners who may be frustrated by scattered information across different sources (zoning docs, cost calculators, contractor advice).

Inference The primary ICP is likely homeowners in areas where ADUs are permitted and economically viable. The product seems tailored for users who are not experts but want reliable guidance.

The description does not provide any evidence of pricing or monetization strategy.

It mentions:

• Stripe integration for purchases
• Server-side receipt verification
• Purchase restoration testing on iOS/Android devices

Inference There is a possibility of monetization via in-app purchases, but no explicit pricing model or revenue streams are described. The presence of Stripe implies some form of transactional flow, though it’s unclear if this is for subscriptions, one-time use, or access to premium features.

The author reports:

• Built with Next.js 16, React 19, TypeScript, Firebase (auth, Firestore, hosting, functions), Three.js + React Three Fiber
• Uses Regrid for parcel data, Google Maps, Stripe
• AI components use OpenAI’s Responses API with gpt-5.6-sol, structured outputs, and bounded tool loops
• Style-match feature uses image understanding + generation (opt-in)
• Mobile support via Android TWA wrapper and iOS shell
• Localized market estimates beyond Bay Area
• Deterministic math engine for core calculations

Inference The tech stack indicates a modern full-stack SaaS product with mobile capabilities, AI integration, and 3D visualization. The use of deterministic logic in core calculations suggests an emphasis on accuracy and reproducibility.

There is no evidence of traction or user adoption beyond the author’s own development work.

The description states:

• The project was built in seven days during a hackathon
• No mention of customers, revenue, or usage metrics
• No indication of beta users or market testing
• No mention of product-market fit or retention

Inference This is an early-stage prototype with no demonstrated traction. It has not yet reached a point where user behavior or engagement can be assessed.

The description does not include any information about competitors or the competitive landscape.

It does not reference:

• Other ADU planning tools
• Zoning checkers or permit guides
• Property data platforms
• AI-powered real estate tools

Inference Without explicit mention of competition, it's unclear whether LotFoundry is addressing a gap in the market or replicating existing solutions. The lack of competitive context makes it difficult to assess positioning.

Key risks and red flags:

• No revenue or customer data: No evidence of monetization or user adoption.
• Single-person team: Only one member listed (Andrew Torralba), which may limit scalability or product depth.
• Unverified claims: All features, functionality, and AI behavior are self-reported without external validation.
• Unclear monetization path: While Stripe is integrated, there’s no clarity on how users pay or what they buy.
• Limited scope in demo mode: The author notes challenges in making the demo mode good enough to showcase the product.

Inference The lack of traction, revenue, and team size raises concerns about viability. The product is still in early development and lacks real-world validation.

1. What specific user feedback or testing has been conducted?
2. How are you planning to monetize this tool? Is there a pricing model or revenue path?
3. Are there any partnerships with local governments, builders, or real estate platforms?
4. What is the current status of Android/iOS app store submissions?
5. How do you plan to expand beyond the current cities and data coverage?
6. What are your long-term goals for product development and team expansion?

Note

These questions aim to uncover gaps in the self-reported description, particularly around traction, monetization, and scalability.