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
Git pre-commit hook prevents AI coding agents from committing with stale documentation
A developer created a Git pre-commit hook that blocks commits when documentation files are outdated, specifically addressing issues with AI coding agents like Claude Code, Cursor, Windsurf, and Copilot. The tool exits with error code 1 to force AI agents to update documentation before proceeding.
Claude Code Plugin /verify: Automated Browser Testing from Your Plan
/verify is an open-source Claude Code plugin that reads your plan, spins up a real browser via Playwright MCP, checks each requirement, and gives you a pass/fail report with screenshots.
Context Routing Layer Reduces Claude Code Token Usage by Tracking Accessed Files
A developer saved approximately $80 per month on Claude Code usage by adding a context routing layer that prevents the AI from re-reading the same repository files on follow-up turns. The tool tracks what files have already been accessed to reduce redundant token consumption.
Needle: A 26M Parameter Tool-Calling Model Built Entirely Without FFNs
Needle is a 26M parameter function-calling model with no MLPs, achieving 6000 tok/s prefill and 1200 tok/s decode on consumer devices. It beats FunctionGemma-270M, Qwen-0.6B, Granite-350M, and LFM2.5-350M on single-shot tool calling.