SmartCited

Note: This analysis is based entirely on the self-reported project description provided by the authors. No external verification, customer data, or financials are available.

The description states that SmartCited:

• Takes a business’s brand and website as input.
• Generates ten unbranded questions about what local customers might ask.
• Sends these questions to both OpenAI and Gemini APIs.
• Records whether the business appears, where it ranks, which competitors appear, and which sources are cited.
• Suggests actions based on this data (e.g., updating a website or Yelp profile).
• Optionally performs those actions with customer permission.
• Saves receipts or public URLs after action completion.

It uses:

• Codex, GPT-5.6, gpt-oss-120b
• OpenAI Responses API, Gemini API
• Puppeteer, Tavily, InsForge, OAuth
• Node.js, TypeScript, HTML5, CSS3, JavaScript

Inference: The product appears to be a proof-of-concept prototype built for a hackathon, not yet a commercial offering. It is described as integrating AI tools into workflows for local business visibility monitoring and action.

The description states:

• SmartCited helps local businesses understand why they may not appear in AI recommendations.
• It aims to improve visibility by identifying where AI gets its information from.
• The tool focuses on unbranded questions to test discovery rather than recognition.
• It compares results across OpenAI and Gemini engines.

Claim: The tool is positioned as a diagnostic and action engine for local business AI visibility.

Inference: This positioning evolved from the idea that businesses often don’t know why competitors are recommended, and that AI answers rely on specific sources like websites, Yelp, or directories.

The description states:

• The target audience is local businesses.
• These businesses may not be known to people searching for services (e.g., “Which dentist in San Francisco is good with anxious patients?”).
• The tool helps them understand how they appear in AI-generated answers.

Claim: Local businesses are the primary users.

Inference: The ICP likely includes small-to-medium-sized enterprises that rely on local search and online visibility, especially those operating in service-based industries where reputation and discoverability matter.

Not evidenced.

Finding: There is no mention of pricing, monetization strategy, or business model in the description. The tool appears to be a prototype built for a hackathon.

The description states:

• Built with Codex, GPT-5.6, gpt-oss-120b
• Uses OpenAI Responses API, Gemini API, Puppeteer, Tavily, InsForge
• Implements OAuth for platform access
• Supports publishing to websites, Yelp, and category directories
• Includes automated checks before action execution (business facts, evidence, permission)
• Passes 41 automated tests and TypeScript checking

Inference: The technical stack suggests a modern SaaS-style architecture using AI APIs and automation. However, the product is described as a prototype with no commercial deployment or production use.

Not evidenced.

Finding: No evidence of revenue, customers, usage metrics, or adoption beyond internal testing and example cases (e.g., Folsom Street Dental). The project was submitted to a hackathon and has not been launched commercially.

Not evidenced.

Finding: There is no mention of competitors or market context in the description. No comparison with existing tools for local SEO, AI visibility monitoring, or business listing management is provided.

• No commercial traction or revenue: The tool is described as a hackathon prototype with no real-world use.
• Unverified claims about effectiveness: The authors note that citations do not prove cause and effect; only a controlled before-and-after test can validate impact.
• Limited platform access: Some platforms (e.g., Yelp) require OAuth or manual verification, which may limit the tool’s full functionality.
• Privacy and permission concerns: The tool requires explicit customer permission for actions, but there is no evidence of how it handles consent or data governance.
• Dependency on AI APIs: Reliance on OpenAI and Gemini APIs introduces risk from API availability, cost, or changes in access.

Inference: SmartCited lacks commercial viability or scalability as described. It is a concept with technical feasibility but no demonstrated market demand or business model.

1. Has the tool been tested with any real local businesses? If so, what were the outcomes?
2. What are the actual costs of running this workflow at scale using OpenAI and Gemini APIs?
3. How does SmartCited handle compliance with platform rules (e.g., Yelp’s terms)?
4. Are there plans to monetize or commercialize this tool beyond the hackathon?
5. What is the current state of the product—does it have a working MVP or is it still in prototype form?
6. How do you plan to validate that actions taken improve visibility, and what metrics will be used?