AI PRD writer
Turn a product idea into a structured product requirements document, full or one-page, in Markdown.
Your key stays in your browser.It goes straight to the provider, never to our servers, and we neither log nor keep it. Use a dedicated key with a spending cap, and delete it in the provider's dashboard when you are done.
Input
Result
The result will appear here.A PRD is where a product idea becomes something engineering, design and the rest of the business can argue about in the same terms: goals, users, scope, requirements and how success will be measured. Paste the idea as you would describe it in a corridor and this drafts the document in Markdown — features in a table marked Must, Should or Could with the MVP picked out, requirements phrased so they can be tested, and non-functional needs such as performance, privacy and accessibility written down instead of implied. Where the idea leaves something open, like pricing, a launch date or a target number, the draft writes [TBD: …] and lists it under open questions rather than making up a figure that then gets quoted in a meeting.
How it works
- Built on Fabric's create_prd pattern, whose section list — Overview, Objectives, Target Audience, Features, User Stories, Functional and Non-functional Requirements, Success Metrics, Timeline — is kept, with Out of Scope and Open Questions added.
- The lean option writes a one-page MVP brief instead: problem, users, goals and metrics, must-have scope, what is out of scope, at most five stories, and the open questions.
- Fabric's instruction to ask for missing information becomes bracketed placeholders, because a single request cannot stop and ask you; every placeholder is a question to settle before the document goes out.
- An unannounced product idea is sensitive, so note where it goes: from your browser to the provider you chose and nowhere else, under a key you can cap in advance and delete when the draft is done.
Where your data goes
With your own key, what you type and the key go from your browser straight to the provider you choose; neither passes through Hysen Labs. In hosted mode, your text goes through our server to our provider (DeepSeek) and is billed in credits; we keep the token counts and cost of each run for billing, never the text itself or the answer. How the provider handles the text is governed by its own privacy policy.
This tool handles keys and credentials, so nothing about a run is saved, not even to your own history.
About your API key
We do not collect, store or leak your key: it lives only in this page's memory (unless you tick “remember in this tab”) and is gone when you close it. Still, treat any key you have pasted into a web page with care — create a dedicated key with a spending cap for use here, and delete or rotate it in your provider's dashboard when you are done.
What it costs
This tool is free, with no sign-in and no points.
Common questions
- Is a generated PRD good enough to hand to engineering?
- It is a first draft that saves the blank-page hour, not a finished document. The model knows what a PRD looks like but not your customers, constraints or strategy, so read every requirement, fill in each [TBD] and delete what does not apply. The success metrics in particular need numbers only you can supply.
- Full or lean — which should I choose?
- Lean for a feature or an MVP that one team will build in a few weeks: it fits on a page and forces the scope question. Full when several teams, a compliance review or an outside stakeholder will read it, because they need the non-functional requirements and the timeline in writing.
- Can I feed it notes from a customer interview or a meeting?
- Yes, paste them as they are. The model separates the product idea from the chatter, but something said only in passing can get promoted to a requirement, so check the Features table against what was actually agreed.
- Which model writes the best PRD?
- Larger models write noticeably tighter requirements and better non-functional sections. A cheaper model is fine for the lean one-pager; for the full document, which is long and read closely, use the strongest model your key can reach.
The open-source behind it
This tool's prompt is adapted from danielmiessler/Fabric (MIT) and runs on the model you choose. To use the same capability from the command line or inside your own program, start with that project.
danielmiessler/FabricAlso known as
- prd template
- product requirements document generator
- ai prd writer
- how to write a prd
- prd example
- mvp requirements document