Hey, we have PDFs being created via Gamma, and then stored to a bank of knowledge. These files need to be referred to easily by agents on our platform, and file names would have a large weighting to allow this. Gamma currently creates these file names by using the title only (we believe) of the presentations it creates. However, sometimes the title is very short/non-descriptive and the subtitle/other headers have the vital context. Therefore, I was wondering if there is a better way to control the file names of the assets created by Gamma. Maybe a parameter we can include while making the generation call to Gamma for the file_name of the asset? That way we can get our ai to come up with the best name for it. Or is there any way that the file_name created by Gamma can use that extra context from the subtitle if the title is short
Hey Advaith (+1 William) -- there's no title parameter on the generation request today. Two workarounds: Put a clear heading as the first line of inputText (e.g., # Q2 2026 Revenue Analysis for Acme Corp). The model usually picks that up as the title. Reinforce it in additionalInstructions: "Title this presentation: Q2 2026 Revenue Analysis for Acme Corp" Not guaranteed, but combining both gets close. A dedicated title param is a clean addition -- log it on the Canny board if you haven't. Your use case (agent-friendly naming for a knowledge bank) is solid justification.
Max J. What about for the name / file_name of the generated asset itself? Is there a way to control that? Or does it deterministically always name it as the title of the deck?
Hi Advaith there isn't a way to control the title of the output file or the gamma itself. It is just deterministic. This isn't the first time I've seen this suggestion so I recommend you post in canny so our product team can take a look.
