tête-à-tête

Company: tête-à-tête

Self-reported basis: The analysis is based entirely on the author's own description of the project, submitted as part of an OpenAI 2026 hackathon entry. No external verification or historical data is available.

What it appears to be: A private digital tool for couples to conduct structured check-ins, with optional live collaboration features.

What changed: The author states that they built the app seriously over a month and ramped up significantly for the OpenAI Build Week hackathon, adding a key feature: live check-ins.

Single most important open question: Is there evidence of any actual user adoption or feedback from couples who have used the tool beyond the initial build?

The description states that tête-à-tête is a private space for couples to have focused check-ins, where partners can choose questions they want to discuss. During a session, users go through the questions one at a time, and can mark them as discussed, add notes, or create actions for follow-ups.

It also supports live check-ins, allowing two partners to join the same session, see when the other is present, and stay on the same question while talking. The app allows viewing past check-ins and tracking shared actions.

Key technical components include:

• Built with React, TypeScript, Vite, Supabase
• Uses GPT-5.6 via Codex for development assistance
• Supabase handles authentication, data storage, security, and real-time updates
• Live sessions are private and only accessible to the couple involved

Inference: The product is a web-based tool designed for intimate relationship communication, with an emphasis on structure and follow-through.

The author claims that couples often want to check in with each other, but these conversations can get lost between messages, calls, notes, and busy schedules. The app aims to provide a calm and private place for meaningful dialogue.

It positions itself as:

• A tool for focused check-ins
• A way to turn conversations into thoughtful actions and follow-ups
• A solution that helps couples make time for meaningful conversations

Inference: The positioning implies a shift from casual communication to intentional, structured interaction. However, the description does not indicate whether this is a new category or an evolution of existing tools like journaling apps or relationship coaching platforms.

The target customer described in the write-up is:

• Couples who want to have regular check-ins
• Users who value private and calm communication
• People looking for a way to follow through on what matters

There is no indication of segmentation beyond this general audience. The author does not specify:

• Whether it targets long-term or new couples
• If there are age, geographic, or cultural demographics
• Any specific use cases beyond check-ins

Inference: The ICP appears to be a broad segment of romantically involved individuals seeking structured communication tools — but the description lacks clarity on how this might differ from other relationship apps or tools.

There is no evidence in the description of:

• A pricing model
• Revenue streams
• Monetization strategy
• Subscription plans or one-time purchases

The author states that they built the app seriously for about a month and ramped up during the hackathon, but does not describe any commercial activity or business plan.

Inference: The project is presented as a personal build with no known monetization path. It may be in early development or intended as a prototype.

The app is built using:

• Frontend: React, TypeScript, Vite
• Backend/Infrastructure: Supabase (including authentication, real-time updates, and database)
• AI Tools Used: GPT-5.6 via Codex for planning, building, testing, and debugging
• Deployment & DevOps: Cloudflare Workers, GitHub Actions

Key features mentioned:

• Live check-ins with synchronization across devices
• Private sessions accessible only by the couple
• Optional notes and action items
• Past check-in history tracking

Inference: The technical stack suggests a modern SaaS-style web app with real-time capabilities. However, no evidence of scaling or production deployment is provided.

The author states:

• They built the app seriously for about a month
• For OpenAI Build Week, they "ramped things up significantly"
• Added a crucial feature: live check-ins

There is no evidence of:

• Users or customers
• Adoption metrics
• Feedback from users
• Product usage data
• Any form of product-market fit

The project was submitted to a hackathon and is described as a prototype.

Inference: The tool appears to be in early development, possibly pre-launch. No signs of traction or user engagement are evident.

The description does not mention:

• Competitors
• Existing tools in the space (e.g., relationship coaching apps, journaling platforms, communication tools)
• Market size or positioning relative to similar offerings

Inference: Without any reference to competitors or market context, it is unclear how this tool fits into the broader ecosystem of relationship and communication tools.

1. No commercial traction or user feedback: The app is described as a hackathon project with no evidence of real-world usage.
2. Unverified claims about AI integration: The use of GPT-5.6 is claimed, but there's no verification that this was actually used in the product or how it influenced design decisions.
3. Lack of clarity on privacy and data handling: While the author says private notes are not sent to OpenAI, there’s no detail on how data is stored or protected beyond Supabase.
4. No monetization strategy: No indication of how the tool would generate revenue or scale.
5. Single-person team: The entire project was built by one person (Tolu A), raising questions about long-term sustainability and scalability.

Inference: This is a personal project with no known commercial viability or user base. Risks include lack of product-market fit, limited resources, and unclear path to growth.

1. What specific problems are you solving for couples that existing tools don’t address?
2. Have you tested the live check-in feature with real users? If so, what feedback did you get?
3. How do you plan to scale beyond a single developer and a prototype?
4. Is there any intention to monetize or grow this product beyond the hackathon phase?
5. What are your plans for privacy, data security, and compliance (e.g., GDPR)?
6. Are you aware of existing tools in this space? How does your solution differ?