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
Reflect MCP Server Implements Reflexion Paper for Persistent Coding Agent Memory
A developer implemented the Reflexion paper (Shinn et al., NeurIPS 2023) as an MCP server to give local coding agents persistent memory of their mistakes. The system uses regex-based pattern matching on error messages and stores lessons in SQLite with FTS5.
Pepper MCP Server for iOS Simulator Interaction and Debugging
Pepper is an MCP server that injects a dylib into iOS simulator apps via DYLD_INSERT_LIBRARIES, enabling real-time interaction, screen reading, button tapping, variable inspection, and network traffic monitoring through a WebSocket bridge.
Orc: Multi-Agent Coding Orchestration Tool Adds Planning and Notification Features
Orc is an open-source tool that orchestrates AI coding agents across projects with a local TUI interface. The latest release adds planning as a first-class phase, notification systems for human intervention, and natural language lifecycle hooks.
Advisor: A /advisor Slash Command for Claude Code That Runs Opus + Parallel Sonnet Runners
A /advisor command for Claude Code runs Opus as a strategist coordinating multiple Sonnet runners that read files in parallel. Found 6 real bugs including a bidi-character trojan source gap.