I build focused automation and data-processing tools designed to solve one job well.

My Actors are built around a few principles:

• Simple inputs and predictable outputs
• Developer-friendly JSON and Dataset schemas
• Clear pricing and documented limitations
• Reliable batch processing and error handling
• AI, RAG, research, and data-pipeline use cases
• Minimal setup and low operational overhead

Current focus:

PDF → RAG-Ready Dataset
Convert public, text-based PDFs into clean, token-aware chunks with page references, Markdown, metadata, stable document IDs, and structured output ready for vector databases, agents, and LLM pipelines.

More utility Actors are planned as individual workflows prove useful.

If you find an edge case, need a feature, or have a high-volume use case, feel free to reach out through the Actor issue system.