Test generation 3

AI-driven code intelligence models for software engineering and coding tasks. Kat Dev is an AI-driven code intelligence offering developed by Kuaishou's Kwaipilot team. It is a family of large language models specialized for software engineering and coding tasks, designed to act like AI engineers. Kat Dev models are capable of understanding complex requirements and generating high-quality code, achieving high performance on benchmarks like SWE-Bench. The models are high-parameter LLMs (32B or 72B) trained specifically for coding with state-of-the-art architectures and extensive reinforcement learning, including multi-stage agentic training with tool use, multi-turn dialogue, and coding knowledge.

AI-powered end-to-end testing and code review for GitHub pull requests TestDriver is an AI-powered code review and end-to-end testing platform for GitHub repositories. It automatically runs pull requests in real desktop sandboxes, interacts with web apps, desktop apps, Chrome extensions, VS Code extensions, and rich media, then detects bugs and creates regression tests. Tests use AI vision rather than selectors or DOM access, run in CI/CD, validate outcomes with AI assertions, self-heal when interfaces change, and provide video replays, logs, action histories, and performance data for debugging.

AI-driven platform for generating notes, tests, and instant answers to supercharge exam preparation. Syllabus.ai is an AI-driven platform designed to supercharge studies and exam preparation. It offers tools to generate notes, tests, and instant answers, aiming to simplify study materials and elevate the learning experience.