Promised

The description states that Promised is a commitment tracker. It allows users to paste raw text (e.g., email threads, Slack exports) and extracts who promised what, to whom, and by when. Users can mark commitments as KEPT or BROKEN in a filterable ledger. A trust ledger shows reliability scores for individuals based on their track record. The tool also supports drafting follow-up messages for overdue items.

It is described as fully browser-based with no backend or signup required. It works offline using an offline regex-based parser and integrates with GPT-5.6 for natural language extraction.

Inference The tool is built for personal or small team use, based on its browser-only architecture and lack of cloud infrastructure.

The author claims that Promised treats sentences like commitments — specifically, those made in meetings, emails, or Slack threads. It positions itself as a solution to the problem of untracked promises in workplace communication.

Inference The tool does not appear to have evolved beyond a hackathon prototype. The author describes it as a “simple” CRUD app with UX depth, suggesting it’s not yet a mature product.

The description states that the tool is for individuals or teams who make and receive commitments in email or Slack threads. It targets users who want to track accountability and reliability in workplace communication.

Inference The target is likely early-stage professionals or small teams with informal communication workflows. No specific ICP is defined beyond this general use case.

There is no evidence of a business model or pricing structure in the description. The tool is described as fully browser-based and offline, with no mention of monetization or paid features.

Inference The project appears to be a prototype with no commercial model defined. It is not evident whether the team intends to monetize it.

Promised was built using React, TypeScript, Vite, and Tailwind CSS. The author used Codex extensively for scaffolding and prompt engineering. It includes an offline regex-based parser as a fallback, and integrates GPT-5.6 for natural language extraction. The UI uses SVG turbulence filters to simulate hand-stamped badges.

Inference The tool is built with modern frontend stack and AI-assisted development. It is not evident whether it has been scaled or optimized beyond the prototype stage.

There is no evidence of traction, revenue, customers, or adoption beyond the project description. The tool is described as a hackathon submission with no mention of user feedback, usage metrics, or product-market fit.

Inference The tool is at a very early stage and not yet proven in the market. No data on usage or retention exists.

There is no evidence of direct competitors mentioned in the description. The author does not reference existing tools for tracking commitments or accountability in workplace communication.

Inference It is unclear whether similar tools exist, and if so, how Promised would differentiate itself.

1. No traction or revenue: The tool is described as a hackathon project with no evidence of adoption.
2. Unproven extraction accuracy: The author notes challenges in natural language extraction and date parsing.
3. Limited scalability: The browser-only, offline approach may not scale for enterprise use cases.
4. No monetization strategy: No indication of how the product would be monetized or whether it is intended to become a commercial offering.

1. What is the current level of promise extraction accuracy? How does it perform on real-world data?
2. Are there any plans to move beyond the browser-only prototype into a scalable product?
3. Has the team considered how this would work in enterprise or team settings?
4. Is there any user feedback or internal testing beyond the hackathon?
5. What is the long-term vision for monetization, if any?