Kadoa
Web scraping platform from Zurich that uses AI agents to build, monitor and self-repair data pipelines when websites change.
What it does
Kadoa collects data from websites and delivers it in structured form. You describe the data you need, and an agent sets up source, data schema and schedule as a workflow. If a page changes and extraction fails, the platform looks for the cause, tests a fix and redeploys it. Every run is checked for completeness and plausibility, and every value links back to where it was found. If you like, Kadoa reports only changes. Results go to Google Sheets, Excel, Slack, Snowflake, Databricks, BigQuery or S3, via webhook, REST API, Python and Node.js SDKs, or into AI assistants through an MCP server.
Who it suits
Mainly finance teams such as funds, asset managers and data providers that track filings, prices or website changes. Also data teams in other industries that regularly need public web data without maintaining their own scrapers.
Data protection for businesses
The operator is reviewr.ai AG in Zurich; the contract is governed by Swiss law. According to the privacy policy, data may be processed in the USA and the EU/EEA; the vendor does not explicitly offer EU-only data hosting. The vendor does not mention a data processing agreement. According to the website, customer data is not used for AI training, but the terms allow anonymized data to be used to improve the services. There is a SOC 2 Type II report, audit logs, and on-premise or private cloud deployment; SAML SSO is part of the Enterprise plan, as are, according to the pricing page, the Snowflake, S3 and MCP integrations.
Limits
The vendor does not publish prices. Whether scraping a given source is legally permitted, for example because of terms of use or personal data, is something you have to check yourself. Features and examples are strongly geared towards financial data.