Coming soon
Prepare sources before they reach AI
The ETL/ELT direction focuses on turning messy web pages, documents, and internal sources into repeatable, structured preparation flows.
- Source intake
- Cleaning
- Chunking
- Index preparation
AI ETL / ELT
AI ETL pipeline direction for source data workflows
The live launch focus is crawler-first. The ETL/ELT direction is intentionally scoped as a production roadmap: connectors, transformations, repeatability, observability, and governance before active checkout positioning.
Current posture
Crawler is liveSearch, scrape, crawl, estimate usage, and export clean website output today.Open Crawler pricingActive plans are metered around crawler credits, not unlimited ETL usage.Open Crawler vs ETLRead the guide explaining how crawler collection and ETL pipelines differ.Open Roadmap questionsAsk about future connector, warehouse, and pipeline needs before public checkout.Open
ETL/ELT production requirements
Coming soon
Production-grade before active selling
ETL/ELT needs connector maturity, durable jobs, retries, audit logs, and clear pricing before it becomes an active public checkout product.
- Connector strategy
- Job observability
- Failure handling
- Pricing separation
Coming soon
Crawler now, pipeline next
The crawler gives teams a practical first step for collecting clean source material while the broader ETL/ELT surface continues toward production readiness.
- Search
- Scrape
- Crawl
- Export
Scope guardrails
Not active checkout
ETL/ELT is not presented as an active paid plan until the full product path is production-ready.
Connector maturity
Production ETL needs durable connector behavior, retries, logs, scheduling, and governance.
Metered costs
Parsing, extraction, embeddings, and transformations should be priced separately from crawling.
Crawler-first revenue
The current public purchase path remains focused on Search + Web Crawler.