Unspoken

What the company appears to be: Unspoken is a self-reported private, AI-guided platform designed for people to express difficult emotions or unfinished words without judgment, with optional gentle responses from an AI. It is described as a mobile-first progressive web app built using React, TypeScript, Vite, Tailwind CSS, Node.js, and the OpenAI API.

What changed: The project was submitted to the OpenAI 2026 hackathon on Devpost by one individual (Peggy Lott), indicating it is an early-stage idea or prototype. There is no evidence of prior development, funding, or commercial traction beyond this submission.

Single most important open question: Is there any evidence that Unspoken has been used by users beyond the author’s own experience and testing?

The description states that Unspoken is a private, AI-guided place to say what was left unspoken, where users can write freely and choose how they want to close the interaction—such as receiving one gentle response, help shaping words for real conversation, or a prayer/faith-based reflection.

It is described as:

• A mobile-first progressive web app
• Built with React, TypeScript, Vite, Tailwind CSS, Node.js, and the OpenAI API
• Designed to offer brief experiences that do not encourage continued conversation or bring back old writing
• Intentionally not a replacement for therapy, friendship, or crisis care

The product is said to use relationship context to guide AI responses, and includes safety routing for possible self-harm or harm-to-others language.

Inference: The app appears to be an experimental tool focused on emotional expression and support, not a commercial product with monetization or scale.

The author describes Unspoken as:

• A private space for difficult feelings
• A place where users can say what was left unspoken
• An experience that helps people leave a little lighter

It is positioned to offer:

• Emotional support through AI
• Choice in response type
• Safety and grounding features
• No streaks, no re-opens, no long-term engagement

The positioning evolves from a personal grief-driven idea into a tool for emotional processing, but the description does not indicate any shift toward broader commercial or market positioning.

Claim: The product is designed to be a safe, private, and emotionally accurate space for people to process grief, regret, conflict, or everyday overwhelm.

The description states that Unspoken is intended for:

• People who have unfinished words or difficult emotions
• Those who want to say what was left unspoken
• Individuals dealing with grief, separation, regret, conflict, love, parenting, or everyday overwhelm

It is not described as targeting any specific demographic beyond those who might benefit from emotional processing or private expression.

Inference: The target customer is likely individuals seeking personal emotional support, possibly in the context of loss, family dynamics, or internal conflict. No segmentation or persona data is provided.

There is no evidence of a business model or pricing structure in the description.

The author states that Unspoken:

• Is not meant to replace therapy, friendship, or crisis care
• Does not create streaks or demand continued conversation
• Is focused on privacy and brevity

No mention of monetization, subscriptions, or paid features is present.

Claim: The business model remains undefined. It may be a prototype or personal project with no commercial intent at this stage.

The product is described as:

• A mobile-first progressive web app
• Built using React, TypeScript, Vite, Tailwind CSS, Node.js, and the OpenAI API
• Uses Codex to refine interaction flow and response modes
• Includes safety routing for self-harm or harm-to-others language

It is said to:

• Use relationship context to guide AI responses
• Avoid generic comfort or impersonation of real people
• Have prompt rules to ensure emotional accuracy
• Include fallback responses for service interruptions

Inference: The technical stack suggests a modern, lightweight web application with AI integration. The use of Codex and prompt engineering indicates an experimental approach to AI interaction design.

There is no evidence of traction or maturity beyond the author’s own description.

The project:

• Was submitted to a hackathon
• Is described as a prototype or early-stage idea
• Has no revenue, customer base, or adoption metrics
• Was built by one person (Peggy Lott)

Claim: No commercial traction or user engagement is evidenced. The product is in an exploratory phase.

There is no evidence of competitors or market positioning beyond the author’s own description.

The author does not reference:

• Similar tools
• Existing products in emotional support or AI therapy spaces
• Market analysis or competitive differentiation

Inference: No competitive context is provided. It is unclear whether Unspoken is unique or part of a broader category of AI-based emotional support tools.

Key risks and red flags include:

• No commercial traction or revenue evidence
• Single-person team, suggesting limited scalability
• Unverified emotional safety features—no external review or testing mentioned
• No pricing, monetization, or business model
• Highly personal and niche use case, which may limit market appeal
• Lack of third-party validation or user feedback

Inference: The project is experimental and lacks commercial viability or market readiness.

1. What specific emotional scenarios have been tested, and how were responses validated?
2. Has the product been used by people outside the author’s own experience?
3. Are there any plans for external safety or mental health professional review?
4. What is the long-term vision for monetization or commercialization?
5. How does the team plan to scale beyond a single-person development effort?