AI writing assistant for academic papers integrated into Microsoft Word
Purpose-built workshop for novelists where you direct narrative architecture while an AI execution engine stays strictly within your guardrails
Stage
Not given
Not given
Founded
Not given
Not given
Based in
DE
Not given
Pricing model
Freemium
Freemium
Pricing
Not given
Free Trial: $0 with 5,000 AI-word pool and no expiry. Starter: $15/month with 50,000 word budget. Novelist: $30/month with 100,000 word budget. Annual plans save 20%.
Key features
Search over 20 million scientific papers using natural language queries
Upload and chat with PDFs up to 1,000 pages per document
AI-powered sentence and paragraph completion in Word with source citations
Deep Review evaluation against nine university grading criteria
Automatic APA 7 citation formatting
Cross-document PDF search within entire project library
Connector integration with Claude and ChatGPT
Own-sources-only mode restricting generation to personal documents
Available on macOS, Windows, and Web App
Blueprint: Lock narrative spine, cast, beats, and voice rules before drafting
Craft Guard: Multi-layered quality screen catching cliché language, named emotions, and sensory bloat
Live Selection Cursor: Highlight text to trigger instant tightening, tense adjustments, and voice alignment
Chameleon Engine: Adaptively matches locked author voice profile and tone
The Ledger: Unified monthly word pool with hard stops and transparent usage tracking
The Forge: Focused revision passes with budgeted refinement pool
Import & Confirm: Upload outlines, cast lists, and notes to populate Blueprint
Proof of Work Certificate: Verifiable export detailing direction history and human-to-assisted balance
Multiple export formats: .txt, .md, .docx, and JSON on paid plans
What makes it different
Integrated directly into Microsoft Word workflow without switching applications
Prevents plagiarism by automatically inserting citations and suggesting paraphrasing
Specifically optimized for academic writing using custom language models
Evaluates work against actual university grading criteria with specific improvement suggestions
All work remains private and never used for model training
True authorship through architectural direction rather than autonomous generation
Strict guardrails that enforce locked voice and narrative rules on every assisted line
Transparent word budgets with hard stops at 100% and no surprise overages
fastwrite
Drafthand™