Tiny Fish provides a platform that enables users to create AI agents for automating and enhancing everyday tasks through intuitive interfaces. This technology simplifies the process of task management, allowing individuals to increase productivity without requiring advanced technical skills.
Funding
$9.3M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Extracting structured data from websites often requires writing fragile parsing scripts using technologies like XPath or CSS selectors, which are prone to breaking due to dynamic content and page structure changes. Existing web scraping methods can be time-consuming and require significant manual effort to maintain.
Solution
AgentQL provides a suite of tools that leverage AI to connect large language models (LLMs) and AI agents to the web, enabling precise and scalable data extraction. The platform features a query language and parser that interacts with web page elements, extracting data quickly and accurately. AgentQL offers a robust alternative to traditional parsing methods by analyzing page structure using AI, ensuring consistent results despite dynamic content and page changes. The platform includes SDKs, a browser-based debugger, and a REST API for versatile integration into data workflows and automation processes.
Target Audience
AgentQL targets developers, data scientists, and AI engineers who need to extract structured data from websites for web automation, scraping, and integration with AI applications.
Features
- AgentQL query language for describing data extraction requirements without needing regex, XPath, or CSS selectors
- Python and JavaScript SDKs for interacting with web page elements via Playwright and headless browsers
- Browser extension for real-time query optimization on any web page
- REST API for retrieving public-facing data from any URL without requiring a browser
- PDF parsing capabilities for extracting tables and data from PDF documents
- Self-healing queries that adapt to dynamic content and page structure changes
- Reusable code that works across multiple similar pages