Ducky

Asimov is a foundational AI-search and vector-search platform built for developers to upload content sources (documents, logs, files, etc.), auto-chunk and embed them, and expose them via a single API to power semantic search, filtering, and relevance for AI agents or applications. It removes the burden of managing separate vector-databases, embedding pipelines, or re-ranking systems by handling ingestion, metadata parameterization, usage tracking, and retrieval logic within a unified architecture. With support for adding content via a REST API and performing semantic search queries with custom filtering parameters, Asimov enables teams to build “search-across-everything” functionality with minimal infrastructure. It is designed to handle metadata, automatic chunking, embedding, and storage (e.g., into MongoDB) and provides developer-friendly tools, including a dashboard, usage analytics, and seamless integration.

Duckie provides AI-powered customer support designed for B2B SaaS companies, helping both customers and support teams quickly access accurate technical information. The AI support agent can automatically respond to support tickets, while the AI support copilot assists agents by searching the company's knowledge base to provide relevant answers. Duckie also offers log investigation, enabling technical support teams to troubleshoot and resolve issues by analyzing error logs, code changes, and customer data. With auto-updates and reminders, Duckie keeps support teams informed about product changes, Jira tickets, and pull requests. It integrates seamlessly into Slack, Zendesk, Microsoft Teams, and Discord, allowing companies to deploy the AI where their customers ask questions. Additionally, Duckie supports drafting responses and providing updates on ongoing tickets, significantly reducing resolution time and enhancing efficiency.