Respello
The inbox that does the work
What it does
Respello handles customer service by reading incoming emails and replying based on your company’s policies, FAQs and knowledge base. It can automatically answer routine messages, hold sensitive or high risk emails for review, flag urgent issues and text your team when attention is needed. You control tone, empathy, formality and response length, while edits and approvals help Respello improve over time.
Respello drafts Gmail replies from your business knowledge. Approve every send, hold risky emails for review, and scale with safe autopilot. 14-day free trial.
Draft-first Gmail assistant grounded in your business knowledge. Risky emails stay human. From smart drafts to team oversight, Respello is built for real customer email, not generic AI chat. Approve AI replies before they send. Start in draft-only and scale when you trust it. Answers grounded in your policies, products, pricing, and FAQs. Hold refunds, legal, angry customers, and sensitive mail for human review. Connect Gmail, teach Respello your business, and start reviewing drafts. No risky surprises. Secure OAuth connection. Tokens stay server-side, never in the browser. Upload docs or paste policies so replies match how you actually operate. Start in draft-only mode. Enable autopilot…from respello.com
Does the same job
all alternatives →More growth this month
the category →
AstraPixels▲267A pixel-art solar system at its real current positions.
Growth · 29d ago · astrapixels.com

Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io


- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io


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