I'm excited to see more about how Papermill and Press can interact with agents in agentic workflows! This seems like a great problem solved in AI-first startups.
Press is designed from the ground-up for agentic workflows. We spoke to hundreds of companies generating PDFs before we designed the language, and had been building AI design systems ourselves for a few years.
It's quite amazing to see what Claude can do when it has a tool like Papermill at its disposal - worth connecting and having a play.
In practice, you can either directly connect an LLM to the MCP server, or send via the API after (say) cleaning up LLM output, combining it with RAG and other data etc.
You can connect an agent to our MCP server, see: https://docs.papermill.io/mcp/#using-the-papermill-mcp-serve...
It's quite amazing to see what Claude can do when it has a tool like Papermill at its disposal - worth connecting and having a play.
In practice, you can either directly connect an LLM to the MCP server, or send via the API after (say) cleaning up LLM output, combining it with RAG and other data etc.