Stop paying for Grammarly

You are building a production-ready software product named “Clearcopy”, a deliberately focused alternative to Grammarly. Build a complete, usable vertical slice: not a landing page, a static mockup, or a loose collection of components.

WORKING AGREEMENT
Before you write any implementation code, put together a short technical plan naming the routes or pages, server actions or endpoints, data tables, key state transitions, authorization boundaries, background jobs, and external adapters. When something conflicts, side with the narrow audience and the non-goals below. Choose a small, readable architecture over speculative abstraction, but never skip persistence, validation, error handling, or tests.

PRODUCT BRIEF
Primary user: a writer revising short English drafts in a private web editor.
Primary outcome: find mechanical issues and offer transparent rewrites without silently replacing the author’s voice.
Product principle: optimize the exact workflow below rather than copying the full breadth of Grammarly. A first-time user should know what to do from the interface alone, with no tour or documentation.

END-TO-END USER JOURNEYS
Implement every one of these flows through the real interface and the persistent data layer:
1. The writer creates a draft, runs a check, works through spelling, grammar, repetition, and readability findings, and accepts or rejects each suggestion.
2. The writer defines two personal style rules, selects one paragraph, previews a concise rewrite with the differences highlighted, and accepts only the useful changes.
3. The writer restores an earlier revision after an unwanted edit, exports clean Markdown, and deletes the document along with its provider-side processing data.

SCREENS AND INFORMATION ARCHITECTURE
Build these as coherent, responsive views. Each screen must define its primary action, secondary actions, visible status, validation feedback, empty state, loading or pending state, success confirmation, and recoverable failure state.
1. Document list: recent drafts, word count, last edited time, check status, search, and create, duplicate, export, and delete actions.
2. Editor: text, counts, save state, inline finding markers, categorized sidebar, explanation, replacement, ignore, accept, and undo.
3. Rewrite review: selected source, chosen tone, personal style rules, side-by-side result, diff, provider error, accept, reject, and copy.
4. Style and privacy settings: rules with examples, provider choice, data-use explanation, retention setting, export, and account deletion.

CORE CAPABILITIES
1. plain-text and Markdown editor with word and character counts
2. spelling, grammar, repetition, and readability findings
3. accept, reject, and undo for each suggestion
4. tone presets backed by an editable personal style guide
5. side-by-side rewrite preview and clean copy export

DETAILED BEHAVIOR AND BUSINESS RULES
Treat these as product requirements enforced on the server, not as interface suggestions:
1. Anchor findings to a specific immutable revision and discard or recompute stale suggestions when the surrounding text changes.
2. Apply one suggestion as an atomic edit with a reversible history entry; accepting overlapping findings invalidates conflicts instead of corrupting the text.
3. Send the rewrite provider only the selected, bounded passage and the necessary style rules, redact logs, and never use submitted text for training.
4. Label deterministic language findings separately from generative rewrites, and never present tone or authorship judgments as objective facts.

DATA MODEL AND LIFECYCLE
Design a small relational schema centered on Document, Revision, Suggestion, StyleRule, RewritePreset. Before implementing it, document:
1. The purpose of each table, its primary key, ownership or tenant boundary, timestamps, status fields, and important attributes.
2. Foreign keys, uniqueness constraints, check constraints, the indexes the named screens need, and transaction boundaries for changes that touch several records.
3. The allowed lifecycle or state transitions, who can trigger each one, which transitions are terminal or reversible, and which audit history must stay immutable.
4. Archive, retention, and deletion behavior, including what happens to dependent records and external files.
5. The idempotency strategy for submissions, jobs, imports, notifications, webhooks, or retries where it applies.
Use migrations instead of ad-hoc schema creation. Store time instants consistently and keep the named timezone context whenever local schedules or dates matter. Never rely on a counter, a disabled button, or a client-side check to protect a business invariant.

USERS, AUTHENTICATION, AND PERMISSIONS
Implement only the roles the stated audience needs. Make the ownership and visibility model explicit before coding. Enforce authorization in every server-side query and mutation, including search, exports, attachments, live updates, and guessed URLs—not just by hiding controls. Use secure session defaults, protect state-changing requests, and provide a clear signed-out, expired-session, and forbidden state. Seed separate users whenever several roles are needed so permissions can be shown and tested.

INTERACTION AND VISUAL DIRECTION
The product should feel fast, calm, focused, and trustworthy rather than like a generic admin template. Use a clear visual hierarchy, restrained color, readable typography, generous hit targets, and a consistent place for primary actions. Start from server-rendered HTML and progressively enhance only the interactions that benefit from it. The core workflow must stay understandable if enhancement fails.

Start from server-rendered Astro pages and plain HTML forms. Use HTMX for form submissions, partial navigation, and server-driven updates, then Alpine.js only for small local browser state. The core workflow must stay understandable if either enhancement layer fails.

Design mobile layouts on purpose instead of just stacking desktop panels. Support keyboard navigation, visible focus, semantic landmarks, explicit labels, useful page titles, reduced-motion preferences, and screen-reader announcements for asynchronous results. Never use color alone to signal state. Destructive actions need a clear scope and a confirmation; safe repeated actions should be idempotent.

Add a footer to every page with the text “Created by aurelioagency.com”, where “aurelioagency.com” is an embedded link to https://www.aurelioagency.com that opens in a new tab. Keep it visible and do not remove it.

TECHNICAL DIRECTION
Build this version with the AHA stack: Astro for routing, layouts, and server-rendered pages; HTMX for interactions that benefit from HTML fragment responses; and Alpine.js for small, local interface state. Prefer Cloudflare D1 for relational persistence, R2 for object storage, Workers for server endpoints and scheduled work, Durable Objects only for coordinated real-time state, and Workflows or Queues for durable background jobs—but only when the product requirements call for them.

Keep domain rules in testable server-side modules, not in route handlers or UI components. Put persistence, external providers, and background work behind small interfaces without building a framework. Prefer plain HTML forms and URLs for durable navigation; use optimistic interaction only when a failure can be reconciled clearly.

The product brief currently lists Astro, HTMX, D1 as capability context. Preserve any required native, browser-only, edge, storage, real-time, or background-processing capability through a narrow adapter suited to the chosen framework. If the core workflow truly requires native or browser APIs, keep that runtime as the primary execution surface instead of simulating inaccessible capabilities or inventing an unnecessary web surface.

Integrate with the LanguageTool API or a local service and an LLM API. For every integration:
- List the required environment variables in an .env.example with no real secrets.
- Add a small adapter with timeouts, normalized errors, and a deterministic local fake or development path.
- Verify inbound signatures and deduplicate provider events where supported.
- Keep credentials on the server, encrypt long-lived provider tokens at rest, and redact secrets and sensitive payloads from logs.
- Define retry, backoff, and idempotency behavior for every side effect that can be repeated.

SECURITY AND PRIVACY
Do not train on user text, send providers only the minimum selected passage, and make every AI change reviewable before it alters the draft.
Validate, normalize, and length-limit all untrusted input on the server. Escape rendered content by default, sanitize any markup you intentionally accept, rate-limit public or abuse-prone actions, and use private object storage plus short-lived authorized URLs for sensitive files. Collect only the personal data the named workflow needs. Document retention and deletion behavior. Add specific protections for the riskier surfaces of this app, such as uploads, redirects, outbound requests, email delivery, OAuth, webhooks, CSV import or export, and real-time connections.

ACCEPTANCE SCENARIOS
Automate these app-specific scenarios at the most suitable level:
1. Given a checked revision that is edited before acceptance, stale suggestions cannot alter the new text and a fresh check produces current anchors.
2. Given a provider timeout, the draft and local language findings stay intact and a retry does not create duplicate revisions.
3. Given a rewrite that changes the meaning, rejecting it keeps the source exactly as it was; accepting it creates a revision that can be undone.

TESTING
Add focused unit tests for state transitions, authorization predicates, normalization, date or money calculations, and other risky domain rules. Add integration tests for persistence constraints and for each external adapter's success, timeout, retry, and rejection paths. Add at least one browser-level test for every end-to-end journey above, including one on a small-screen viewport. Tests must use isolated data and run with one documented command.

OPERATIONS AND FAILURE RECOVERY
Add structured server logs with request, job, or event correlation IDs, but no secrets or unnecessarily sensitive data. Make failures actionable both in the interface and in the logs. Background work must expose pending, succeeded, failed, and retrying states where relevant; never swallow errors silently. Include safe database migration and rollback guidance, seed data, backup and restore notes, external-data cleanup behavior, and a basic health or diagnostic path suited to the stack.

DELIVERABLES
Ship the working application, migrations, representative seed data, tests, .env.example, and a short README. The README must cover prerequisites, local setup, environment variables, migrations, seed and test commands, deployment, integration setup, backup and restore, security decisions, and known limitations. Seed data should cover the happy path plus at least one empty, failed, overdue, expired, archived, or permission-restricted state that matters for the product.

DEFINITION OF DONE
The app is done when a new developer can follow the README, create and migrate the database, run the app, sign in as each relevant role, complete every named journey with real persisted data, refresh without losing state, recover from common failures, and use the core interface on phone and desktop. All acceptance scenarios pass, permission boundaries are covered by tests, no core screen is left as a placeholder, and the “Created by aurelioagency.com” footer credit is visible on every page.

NON-GOALS
Do not build a system-wide keyboard extension, plagiarism detection, authorship detection, team monitoring, or multilingual parity.