MakeToday

Note: This analysis is based entirely on self-reported information from the author. No independent verification, revenue, customer data, or traction metrics are available.

The description states that MakeToday is an app that gives users three personalized activity recommendations based on their current situation. It allows customization using factors like mood, time, budget, location, and preferred travel method.

It includes:

• A recommendation engine that evaluates user inputs
• Simulated or curated data (e.g., places, weather, travel times)
• Local browser storage for preferences and usage history
• A "My Days" journal feature to log completed activities

The app is built as a mobile-first web experience using Next.js, TypeScript, Tailwind CSS, and React.

Inference: The product appears to be a lightweight, AI-assisted prototype with no live data integration or user accounts at this stage. It is not described as a commercial service or platform.

The author positions MakeToday as a solution for people who struggle with decision-making or feeling stuck between wanting to do something and figuring out what to do. The app aims to reduce the burden of choosing by tailoring suggestions to the user's actual situation.

Key claims:

• It removes overwhelm from abundance of options.
• It provides flexibility while avoiding long lists.
• It helps users get started more easily, especially those with anxiety or decision fatigue.
• It offers a simple interface that doesn’t feel like another chore.

Claim vs Fact: These are self-reported intentions and perceived benefits. There is no evidence of user feedback, adoption rates, or behavioral data to confirm these claims.

The author describes the target audience as:

• People who struggle with decision-making
• Those who find it hard to get started doing something
• Individuals dealing with anxiety or decision fatigue

They note that it may be especially useful for people who "struggle more with decision-making, anxiety, or finding the push to get out and do something."

Inference: The app seems aimed at a broad but underserved segment of users looking for low-effort activity suggestions. No specific persona or segmentation beyond general psychological traits is described.

There is no evidence in the description of any business model, pricing strategy, monetization plan, or revenue streams. The project is presented as a prototype built during a hackathon and does not mention subscriptions, ads, partnerships, or paid features.

Not evidenced: No indication of how the product would generate value or income.

The app was built using:

• AI tools (Codex, GPT-5.6)
• Technologies: Next.js, TypeScript, Tailwind CSS, React, Playwright, Vitest, Vercel
• Local storage for data persistence
• Browser-based UI with mobile-first design

It uses deterministic local recommendation logic and simulated inputs rather than live APIs or databases.

Inference: The technical stack suggests a lightweight, frontend-heavy prototype. There is no evidence of backend infrastructure, scalability planning, or integration with external services.

The project has:

• No reported users, customers, or adoption metrics
• No revenue or monetization data
• No mention of growth, retention, or usage statistics
• Is described as a prototype built in a hackathon context

Not evidenced: There is no evidence of traction, user engagement, or product-market fit beyond the author’s own account.

There are no references to competitors or existing solutions in the description. The author does not compare MakeToday to similar apps or platforms that offer activity recommendations or decision support tools.

Not evidenced: No competitive landscape or differentiation analysis is provided.

• Single-person development: The entire project was built by one person (Conrad Damrau), raising questions about scalability, long-term maintenance, and team capacity.
• Prototype-only status: The app is described as a curated prototype without live data or real-world integration.
• No commercial viability: No evidence of monetization, business model, or user base.
• AI dependency: Heavy reliance on AI tools (Codex, GPT) raises concerns about reproducibility and control over the product if those tools change or become unavailable.

Inference: The lack of traction, revenue, or team structure suggests a high risk of failure unless significant progress is made post-hackathon.

1. What specific user feedback have you received about the prototype?
2. Are there any plans to integrate live data sources (e.g., weather APIs, place databases)?
3. How do you plan to scale beyond a single developer?
4. Have you tested the app with real users outside of your own testing?
5. Is there any intention to monetize or build a sustainable business model?
6. What are the key assumptions behind the recommendation logic, and how will they evolve?