Lex

Analyzes document context and writing style to generate contextually relevant completions and suggestions as users type. The system likely maintains a rolling context window of recent paragraphs and document metadata to inform completion quality, integrating with underlying LLM APIs to produce suggestions that match tone and intent without requiring explicit prompts.

Allows users to select text passages and request rewrites with specific intents (tone adjustment, clarity improvement, brevity, expansion). The system sends selected text plus user intent to an LLM backend, which generates alternative phrasings while preserving semantic meaning. Likely implements a selection-to-rewrite pipeline with undo/redo support for iterative refinement.

Maintains document version history and uses AI to analyze and summarize changes between versions. The system tracks edits, generates human-readable summaries of what changed and why, and allows users to understand document evolution without manually comparing versions. Likely implements diff analysis with LLM-powered interpretation.

Generates concise summaries of document sections or entire documents by analyzing content structure and identifying key points. The system likely uses extractive or abstractive summarization techniques, processing document text through an LLM to produce summaries at configurable lengths (bullet points, paragraphs, etc.).

Continuously analyzes document text for grammatical errors, style inconsistencies, and clarity issues, providing inline suggestions with explanations. The system likely uses a combination of rule-based grammar checking and LLM-based style analysis, flagging issues with context-aware corrections that preserve the user's intended meaning.

Analyzes document content or user prompts to automatically generate document outlines and hierarchical structures. The system processes text or user intent through an LLM to create structured outlines with headings, subheadings, and logical flow, which users can then expand into full documents or use as writing guides.

Allows users to specify target audience or desired tone, then adjusts document language and style accordingly. The system maintains audience/tone metadata and uses it to inform all AI suggestions (completions, rewrites, grammar checks), ensuring consistency throughout the document. Likely implemented as a document-level configuration that influences LLM prompts.

Supports real-time collaborative document editing with AI-powered conflict resolution when multiple users edit simultaneously. The system likely tracks changes, detects conflicts, and uses LLM reasoning to suggest intelligent merges that preserve intent from both users rather than simple last-write-wins or manual resolution.

Analyzes claims in documents and suggests fact-checking or provides context about potentially questionable statements. The system may integrate with search APIs or knowledge bases to flag unsupported claims, suggest sources, or provide context. Likely implemented as an optional analysis pass that highlights claims requiring verification.

Provides document templates (letters, proposals, reports, etc.) that users can customize with AI assistance. The system fills template placeholders intelligently based on user context and preferences, using LLM to generate appropriate content for each section while maintaining template structure and formatting.

Enables writing and editing in multiple languages with AI-powered translation between languages. The system detects language context and can translate selected text or entire documents while preserving formatting and style. Likely uses neural machine translation APIs integrated with the editor.