AI writing assistant for academic papers integrated into Microsoft Word
Datasets for RAG, fine-tuning and training built from public sources
Stage
Not given
Not given
Founded
Not given
Not given
Based in
DE
Not given
Pricing model
Freemium
Paid
Pricing
Not given
Web Corpus: starter sets from $49 (250,000-500,000 documents); shelf corpora from $99-$199 per shelf (one-time license); Everything (full crawl) $3,000 one-time; Whole Library (all builds for one year) $5,000 per year. Reference Collections: Encyclopedia $1,200 commercial or $349 research (one-time)
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
Web corpus with 100.7M documents and 105B tokens from Common Crawl
Documents scored with Bear Rank and shelved by subject
15 million encyclopedia entries with sources and model attribution
200 million synthetic Q&A records with metadata
Delivered as JSONL and Parquet formats
Free samples available on Hugging Face
Command-line client with resumable downloads and SHA-256 verification
Statistics collection with 7,000 topics and 140,000 figures
Glossaries for 10,000 topics with one million definitions
Book Q&A dataset with 8,000 titles for reading comprehension
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
All datasets built only from public sources with full provenance tracking
Every record includes source attribution and licensing information
Eight curated subject shelves for targeted corpus selection
Flexible purchasing: buy individual shelves, slices, or entire library
Over 4 TB of clean, deduplicated text ready for machine learning
fastwrite