Revise: AI Editor Built with Agentic Coding Tools and Y.js CRDT
Technical Implementation
Revise was built over 10 months using agentic coding tools, with the developer reporting never moving faster in their development career. The architecture includes a word processor engine and rendering layer built entirely from scratch. The only third-party library used is Y.js for the CRDT (Conflict-Free Replicated Data Type) stack.
AI Features
The editor integrates multiple AI models for document processing:
- GPT-5.4 Mini
- GPT-5.4
- GPT-5.4 Pro
- Claude Haiku 4.5
- Claude Sonnet 4.6
- Claude Opus 4.6
The AI agent works side-by-side with users in the same interface, providing inline proofreading and revision suggestions. It can detect inconsistencies in documents, such as timeline mismatches or contradictory statements about revenue changes.
Document Processing Capabilities
- Import Word documents and Google Docs
- Extract content from PDFs using multi-modal LLMs
- Proofread, revise, and perfect existing documents
- Export functionality with various settings
User Customization
Revise learns user preferences over time, including:
- Pronoun preferences (e.g., they/them)
- Feedback style preferences (direct vs. fluffy praise)
- Spelling preferences (US vs. other variants)
- Formatting preferences (APA 7, Oxford comma usage)
- Tone preferences (warm and precise, avoiding exclamation points)
- Accessibility considerations
- Document structure preferences (short paragraphs, concise drafts)
Technical Writing Preferences
The system supports specific technical documentation requirements:
- Performance claims must include benchmark setup, workload shape, sample size, and baseline comparisons
- Preference for concrete API contracts with request/response payloads, pagination rules, and idempotency semantics
- Breaking changes must be called out (API changes, data backfills, index migrations, client version gates)
- Requirements as numbered acceptance criteria with edge cases, retry behavior, and expiration details
- Trust in metrics like p95s, error budgets, queue depth, and incident counts over adjectives
📖 Read the full source: HN AI Agents
👀 See Also
Four ClawHub Skills for Real-Time Search Data in AI Agents
Four ClawHub skills provide structured search capabilities for AI agents: Google (web, news, images, maps), Amazon (product search across 12 marketplaces), Walmart (product search with delivery filters), and YouTube (video search with transcripts). Install via clawhub install commands with one API key.
Mengram AI: Auto-Memory Tool for Claude Code Sessions
Mengram AI automatically maintains context between Claude Code sessions by loading cognitive profiles, injecting relevant past context into prompts, and saving new knowledge. It stores semantic, episodic, and procedural memory that evolves based on failures.
Using Claude to Automate Mobile App QA with Capacitor WebViews
A developer built an automated QA system using Claude to test a Capacitor-based mobile app across Android and iOS. The approach uses Chrome DevTools Protocol for Android WebViews and screenshots for visual analysis, with Android setup taking 90 minutes versus 6+ hours for iOS.
altRAG: Replace Vector DB RAG with 2KB Pointer Files for AI Coding Agents
altRAG is a Python tool that replaces vector database RAG with lightweight pointer files. It scans Markdown/YAML skill files to create a 2KB skeleton file mapping sections to exact line numbers and byte offsets, allowing AI agents to read only needed sections instead of entire files.