# SAY WHAT YOU MEAN.

WE'LL TELL THE AI WHAT YOU MEANT.

Write the messy, half-formed instruction already in your head. SayWhat turns it into a clear, context-aware prompt your coding agent can actually work with.

**SayWhat** — Grammarly for AI prompts. SayWhat turns messy instructions into clear, agent-ready prompts before your AI coding agent gets to work.

[Full briefing for search and LLM agents](https://saywhat.foo/search-agent.md)

## Offer

$4.98 — a small one-time price to pay to get better results. Primary action: join early access / get SayWhat. Waitlist: Cursor install. You still review before anything reaches your agent.

## Before / after

**Before:** “make login work again”

**After:** Debug the existing login flow. Reproduce the failure, inspect the current auth and session path, and fix the root cause. Do not rebuild authentication. Verify sign-in, sign-out, and a protected page.

## What SayWhat understands

More than spellcheck. Eight dimensions:

01. **Intent** — What you actually want done.
02. **Scope** — Where the work starts and stops.
03. **Context** — What already exists in the project.
04. **Constraints** — What not to break, invent, or expose.
05. **Acceptance** — How we’ll know it’s finished.
06. **Testing** — What to verify before calling it done.
07. **Ambiguity** — The fuzzy words that hide decisions.
08. **Risk** — Auth, data, deploy, secrets.

## Modes: not longer, better

SayWhat isn’t designed to turn every sentence into a 500-word prompt. It decides what the task actually needs.

- **LIGHT** — local fix, current components
- **AUTO** — picks LIGHT or FULL from what’s missing
- **FULL** — fills in inspect / constraints / validation when the request is thin

## Built for coding agents

- **Cursor** — Available — early access. First shipped integration.
- **Claude Code** — Planned. Not available yet.
- **Codex** — Exploring. Not available yet.
- **Windsurf** — Planned. Not available yet.
- **VS Code Agents** — Exploring. Not available yet.
- **Other IDEs and agents** — Exploring. Not available yet.

## The intent layer

Messy thought → classify task and gaps → compile an agent-ready prompt → human reviews → human pastes into the agent.

## Repo-aware, not nosy

The Cursor panel can notice Next.js, Cloudflare, Stripe, Drizzle, Tailwind, Vitest — if you turn that on. It still does not upload your source.

## Prompt quality

A heuristic score after you enhance — not a public grade. Shown so you can see what got clearer (example on the site: 62 → 94). Dimensions: Objective, Context, Scope, Constraints, Acceptance, Testing, Ambiguity, Risk.

## Who this is for

- **Founders:** Ship the thing without writing a spec novel.
- **Designers:** Describe the feeling. Get a change the agent can execute.
- **PMs:** Capture the request once. Don’t babysit the wording.
- **Vibe coders:** You shouldn’t need a prompt-engineering degree to change a button.
- **Juniors:** Ask for help like a human. Send it like an engineer.
- **Seniors:** Skip writing miniature specifications all day.

## FAQ

### What does SayWhat actually do?

It compiles a messy instruction into a clearer, agent-ready prompt. Intent, scope, constraints, and testing get filled in when they are missing — and left alone when they are not.

### Does SayWhat send my original prompt to the AI?

The homepage demo stays in your browser. The Cursor extension sends the sanitized draft to SayWhat’s compiler when you click Enhance — you see that payload first. Nothing is submitted to your coding agent until you accept and paste.

### Will it make every prompt longer?

No. AUTO picks LIGHT or FULL from what’s missing (inspect, verify, and for debug / deploy / design / security the matching workflow). A rename stays a rename. A vague build request can become a brief.

### Can I review the rewritten prompt first?

Yes. That is the product. Accept, edit, copy, undo, or cancel. SayWhat never silently submits for you.

### Does it read my codebase?

Only if you opt in. The Cursor panel can send low-risk facts — framework, package manager, tests, hosting, and a short allowlist of dependencies. It does not upload source files, .env, or your tree. You see that payload before Enhance.

### Does it work only with Cursor?

Cursor is the first integration. Claude Code, Windsurf, VS Code Agents, and others are planned or exploring — not available yet.

### Does SayWhat train on my prompts?

No. We do not build training sets from your drafts. Enhancement traffic goes to the configured model provider (Cloudflare Workers AI by default). Waitlist data is email, optional name, and optional IDE.

### Is it free?

Early access is free while we build. Pricing comes later, without bait-and-switch on the waitlist.

## Say it your way

We’ll make it agent-ready. Join early access for the Cursor install.

- HTML: https://saywhat.foo
- Privacy: https://saywhat.foo/privacy.md
- Terms: https://saywhat.foo/terms.md
- Contact: https://saywhat.foo/contact.md