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
Claude Proposal: Scope Memory & Hermetic Instance Isolation
A formal proposal to Anthropic from a power user: global/local memory scoping and hermetic instance isolation for Claude, enabling deterministic, auditable sessions.
OpenUtter: Query Google Meet Transcripts Live via OpenClaw
OpenUtter is a skill that joins Google Meet as a guest via a headless browser, captures live captions, and streams them to your OpenClaw event bus. You can query the live transcript mid-call via Telegram, WhatsApp, Slack, or Discord.
AgentPeek: Open-source dashboard for monitoring Claude Code agent teams
AgentPeek is a local dashboard that hooks into Claude Code to provide visibility into agent teams, showing orchestration hierarchies, execution traces, token costs, and file operations. Installation requires cloning the GitHub repo and running pipx install.
Mole: Deep-Research Agent with Enforced Budget and Verified Quotes for Your Terminal
Mole is a terminal-based deep-research agent that enforces a hard budget (0% overshoot), verifies every claim with quotes, and keeps local data private. Supports most LLMs and MCP.