Krino

What it does

Most fraud tools are black boxes you ship customer data to. Krino inverts both. It runs inside your infrastructure — transactions, devices, enrichment and sanctions lists never leave. Analysts build rules visually, shadow-test a draft against live traffic to see what it would change, then publish. No deploy. Every decision comes back rule by rule, with the data as it was — replayable months later. The AI assistant runs on your model and key, read-only, PII stripped before it leaves.

İşlemleri ve kullanıcı hareketlerini gerçek zamanlı değerlendirin, her kararı gerekçesiyle savunun. Kuralları risk ekibiniz yazar, veri kurumunuzdan çıkmaz. Kendi sunucunuzda çalışır.

Krino her işlemi kendi kurallarınızla değerlendirir ve hangi kuralın kaç puan kattığını kayda geçirir. Denetçiye bir sayı değil, gerekçe gösterirsiniz. Örnek bir sanal POS işlemi. Kuralları tek tek kapatın: skor, sonuç ve kayda geçen gerekçe aynı anda yeniden yazılır. Üründe her kararın yanıtı bu ayrıntıyı taşır. Bir kuralı kapatmak için üzerine dokunun. Bu senaryoda inceleme 30, engelle ve incele 60 puanda başlar. Engelle ve incele, skor 92 (eşik 60). Katkı veren kurallar: geçici e-posta sağlayıcı +40, datacenter IP çıkışı +30, aynı cihazda 24 saatte 6 kart +22. Dolandırıcılık deseni bir haftada değişir. Kuralın değişmesi bir sürüm bekliyorsa, o hafta zarardır. Risk ekibi deseni fark eder,…from krino.uk

• 
  KastraJul 2026 · kastra.ai · ▲332

  Hi HN, Fernando and I built Kastra. Kastra intercepts AI agent tool calls and evaluates them against deterministic policies before they execute. We built this product to control pre- and post-inference workloads. This is aimed at developers using coding agents like Claude Code, Codex, Cursor, and OpenClaw. Kastra pushes an allow, hold, and deny decision before the action runs. You can build these policies in plain English from the web app. The interception engine evaluates the tools, targets, and parameters of every action at sub 1ms at a scale of billions of interceptions per day. We also…

• 
  Is My CEO A Fraud?2025 · ▲262

  Figure out how likely an entrepeneur is to commit fraud

• 
  Flagright AI Forensics2023 · flagright.com · ▲108

  The modern standard in AML compliance through AI agents

• IB
  I built an AI tool to analyze SEC filings the minute they're released2024 · docdelta.ca · ▲62

  Hello everyone, I built this tool on Next/Node to automatically analyze new filings from the SEC and probe the Edgar API for new filings 24/7. We use AI to analyze the filings the second they are released. Free accounts to look at real filings (automatically updated) are available to any who sign up. If you have any questions feel free to ask.

• 
  Kelet – Root Cause Analysis agent for your LLM appsApr 2026 · kelet.ai · ▲47

  I've spent the past few years building 50+ AI agents in prod (some reached 1M+ sessions/day), and the hardest part was never building them — it was figuring out why they fail. AI agents don't crash. They just quietly give wrong answers. You end up scrolling through traces one by one, trying to find a pattern across hundreds of sessions. Kelet automates that investigation. Here's how it works: 1. You connect your traces and signals (user feedback, edits, clicks, sentiment, LLM-as-a-judge, etc.) 2. Kelet processes those signals and extracts facts about each session 3. It forms hypotheses…

• 
  KakuninMay 2026 · kakunin.ai · ▲20

  Cryptographic identity for autonomous AI agents

• TL
  The load-bearing vocabulary of Claude▲710

  Life & fun · Aug 2026 · louisabraham.github.io

• 
  Hey Noah▲656

  A proactive AI executive assistant for founders

  AI · Aug 2026 · heynoah.io

• 
  Clipto MCP▲655

  Hey HN, We recently built Clipto. It’s a tool that lets you search over terabytes of video, audio, and images on your computer, without relying on the cloud. Motivation: we probably all had this similar experience, we know a moment exists in a video or audio, but finding it takes hours scrubbing the timeline. You can send all the media to process in the cloud, but it’s slow, expensive and raises privacy concerns. So we decided to build our own on-device media search engine. How it works (high level): 1. We ingest video, audio, image; normalize formats via ffmpeg; run content analysis to…

  Work · Aug 2026 · clipto.com

• 
  Simple algorithm and color space to generate diverse skin tones▲627

  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

• 
  AdAnt AI▲620

  Claude for viral, high-converting social ads

  AI · Aug 2026 · adant.ai

• 
  Astute▲606

  Automate your B2B brand going viral, with new media creators

  AI · Aug 2026 · company-app.joinastute.com