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
New Structured Data API Provides Subscription Pricing for LLM Agents
A developer has released a structured data API that normalizes subscription pricing across streaming platforms, ride-share services, dating apps, and other subscription-based platforms. The API provides consistent JSON schemas, region-aware pricing where available, and MCP-compatible endpoints for LLM agents to consume without scraping.
LTM: A JSON Protocol for Portable Agent Memory Across Models and Machines
LTM is a JSON protocol (Core Memory Packet) plus CLI/server for persisting agent context—dead ends, constraints, next steps—across models, editors, and machines. Packets are 2-5 KB, redact secrets, and support MCP.
Oh-My-Mermaid: Claude Code Skill for Auto-Generating Architecture Diagrams
Oh-My-Mermaid is a Claude Code skill that analyzes codebases and automatically generates Mermaid architecture diagrams and documentation. It's installed via npm and used with the /omm-scan command in Claude Code.
OpenClaw Skill Connects Agents to Knods.io UI for Workflow Creation
A developer has built an OpenClaw skill that enables agents to understand and create workflows within the Knods.io UI, allowing users to switch between specific agents like brand-specific ones instead of relying on Knods' built-in agent.