PromiseProof
Every promise a company makes, quoted word for word
What it does
Paste any company's pricing page. PromiseProof pulls out every consequential promise — guarantees, performance figures, superlatives, breadth claims — quoted word for word, and flags which ones a careful buyer would want evidence for. It never calls a company dishonest. It says what was promised, in their words, before you're six months into a contract arguing about it. Free, no account, no email. Deterministic, not an LLM — if the wording isn't on the page, it isn't in your result.
Paste any company's page. We extract every consequential promise word for word and tell you which ones a careful buyer would want evidence for. Free, instant, no account.
Paste any company’s pricing or product page. We pull out every consequential promise — guarantees, performance figures, superlatives, breadth claims — word for word, and tell you which ones a careful buyer would want to see evidence for before paying. Free. No account, no email address. We read only the page you name, and only what its robots.txt allows. The promises on a sales page are the ones you will want to hold a vendor to later, and they are also the ones nobody writes down before signing. Six months on, the argument is about what was said, and the page has quietly changed. This does not tell you a company is dishonest, and it never will — that is a legal conclusion and we do not…from kema.knightbyrd.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 · 16d ago · simedw.com