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
Multi-Agent System for Deep Competitive Analysis with Claude
A developer built a three-wave agent system that moves beyond shallow competitor lists to extract pricing intelligence, customer sentiment patterns, and strategic signals through structured multi-source research.
InsForge: Self-Hosted Postgres Backend with MCP Integration for AI Coding Agents
InsForge is an open-source, self-hosted backend alternative to Supabase that connects to Claude Code via MCP, allowing AI agents to see schema, policies, and service state. It includes PostgreSQL 16.4, PostgREST, Deno Runtime, auth, storage, and edge functions.
Fino: Open-Source MCP Server for Personal Finance Analysis with Claude
Fino is a free, open-source MCP server that connects Claude to bank accounts through Plaid, stores transaction data locally in SQLite, and provides Claude with tools for financial analysis.
Commitment Issues: A Tool That Analyzes and 'Buries' Unfinished GitHub Repos
A developer built a tool called Commitment Issues that analyzes GitHub repositories to determine if they're abandoned, generates a 'death certificate,' and extracts the final commit message as 'last words.' The tool uses heuristics like commit frequency, last activity, and stars vs momentum, and was prototyped using Claude.