"Hello, I am building an agent using Botpress Viber, on the free Pay as you go plan. My use case requires the agent to read text content from PDFs and images attached by users during the conversation, for example payslips to analyze. I understand this feature is called Vision Agent and is configured through the Autonomous Node in Botpress Studio, but I cannot find a way to access the Studio view from my agent created in Viber. Could you tell me how to enable this feature, and whether it is available on the free plan or requires an upgrade?"

With Botpress Viber, you don’t access the old Studio workflow/Autonomous Node interface—Viber uses its own conversational builder, Vibe. The current docs show that Vision Agent configuration is a Studio feature, while Viber has a separate architecture. So I’d first verify whether your Viber agent currently supports incoming-image extraction rather than trying to enable the Studio setting. I can help check the correct setup for PDF/image uploads and whether your plan supports it.. @refined-state-94922