FAQ

Eight questions we hear most.

If yours is not here, mail us — short answers come back fast.

What does FileDigest actually do?

It takes one or more files, such as PDFs, DOCXs, slides, or folders, and produces one ordered Markdown document with section headers, tables, code blocks, and source-file metadata preserved. You paste that document into any LLM. We do not run the LLM for you; we hand you a clean input.

How long does processing take?

A typical 4.5MB cold-start run finishes in about 62 seconds. The same file warm comes back in roughly 17 seconds. Larger jobs scale roughly linearly with token count.

What file formats do you support?

PDF and DOCX are the primary formats. PPTX, XLSX, HTML, Markdown, plain text, common image formats, ZIP batches, and folder picks are supported where the parser can read them.

Do you keep my files?

Source files are deleted from object storage immediately after a successful job unless you explicitly opt to retain them. Processed digests stay 7 days on Free, 30 on Pro, 90 on Business. Full details in our privacy policy.

How is pricing measured?

In LLM tokens — the same units the model sees, roughly 1,000 tokens per 1.5 pages of typical PDF. Free is 3M tokens / month. Pro and Business scale up. See the breakdown on /pricing.

Is there an API?

Yes, but it is a Business/private-beta feature while key issuance and rotation finish. See /docs/api for the latest.

What are IU72 panels?

A 12-panel HTML snapshot of the document — opening frame, context, drivers, mechanism, evidence, and so on — derived directly from the source. Useful as a visual companion to the Markdown digest. Full description on /docs/iu72.

Where do I report a bug or ask for a feature?

Email hello@filedigest.app. We read everything. Bug reports with the job id and a brief description are most useful.