Workbench AI
Transform rough ideas into structured diagrams with AI
What it does
Chat with Claude to brainstorm and architect ideas on an infinite canvas. Unlike regular AI chat, Claude directly creates, connects, and organizes nodes on your diagram in real-time — not just text responses. Describe a SaaS architecture, product launch plan, or investor pitch, and watch it take shape visually. Refine through conversation: restructure, add detail, explore alternatives. Multiple conversation threads per project. Auto-layout. Dark mode. Free to start, Pro for $20/mo.
Does the same job
all alternatives →
Claude Design by Anthropic LabsApr 2026 · claude.com · ▲551Make prototypes, slides & one-pagers by talking to Claude
Slides AI PluginApr 2026 · proyecto26.com · ▲7Turn any idea into a full presentation from a single prompt
- APAgent PromptTrain – Manage Claude Code Conversations for Teams2025 · github.com · ▲5
I've been working on this internal project initially both to learn more Vibe-Coding but also to help our teams and projects to use AI more efficiently. As more people used it, it grew to support multiple teams/projects to analyze their Claude Code conversation and optimize them over time (understanding how to write better conversation with Claude Code and share knowledge between them) With time we added support for multiple Claude account management and monitor usage/rate limit. This is a simple project but has proved to be quite useful for our company. We have reached 5000+…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
