ExoTest

Parea AI: Experimentation and human annotation platform for AI teams to ship LLM apps. Parea AI is an experimentation and human annotation platform designed for AI teams. It provides tools for experiment tracking, observability, and human annotation, helping teams confidently ship LLM applications to production. Parea AI offers features such as auto-creating domain-specific evals, performance testing and tracking, debugging failures, human review, prompt playground, deployment tools, observability, and dataset management.

Basin MCP stops AI code generation hallucinations and improves code reliability through testing. Basin MCP is a reliability MCP tool designed for AI code editors like Cursor and Windsurf. Its primary function is to stop code generation hallucinations by extensively testing your copilot’s output and feeding the test results back to the copilot for automatic improvement. This ensures that your code editor generates reliable, quality code, allowing users to create applications without the fear of AI-generated bugs or inconsistencies. Basin MCP instantly identifies and flags problems, enabling faster and more confident 'vibe coding'.

AI-powered autonomous browser agents for QA automation. Propolis automates away all QA needs by developing intelligent agents that can understand and walk through your application, surfacing bugs and errors as they find them. It unleashes AI swarms that eliminate manual QA by testing like real users. Its autonomous browser agents explore all product flows, find bugs, and adapt instantly to changes, allowing users to ship faster with confidence.

AI platform for building custom evaluation and scoring systems for LLMs. Pi Labs offers an AI-powered platform designed to automatically build evaluation systems (evals) for AI applications, particularly those involving Large Language Models (LLMs) and agents. It enables users to create custom scoring models that precisely match user feedback and prompts, ensuring highly accurate and consistent evaluation. The platform integrates seamlessly with various existing tools and provides a fast, highly accurate foundation model called Pi Scorer for comprehensive metrics, observability, and agent control across the entire AI stack.

AI platform for battle-testing and improving AI agents. Janus is an advanced AI platform designed to battle-test and improve AI agents. It conducts thousands of AI simulations against chat and voice agents to surface critical failures such as hallucinations (fabricated content), rule violations (policy breaches), and tool-call/performance failures. Janus offers custom evaluations, personalized datasets, and actionable insights to help users detect and mitigate risky agent behavior, ensuring model reliability and performance.