demo

See Papayya on your workload

Thirty minutes: twelve of demo on a real 150-page document, the rest on your workload and where its items come from. Papayya runs in your cloud and reads your data where it already lives.

The demo is one incident, run end to end. A batch of 150 pages reports success. Page 73 came back blank — nothing raised, nothing retried, the exit code was 0. Then we re-drive page 73 on its own: one page execution, not three hundred. Last, what the run cost, broken down by which of your customers it belonged to.

If that is a Tuesday you recognise, the rest of the call is about your workload rather than ours.

What we will ask

• What happens today when a batch finishes and something in it was wrong.
• Which pipeline you would point at this first — a named one, not a category.
• Roughly how many items a day, and what a single item looks like.
• Where those items live today, and whether the id or the payload should travel.
• Where it would run: Papayya installs into infrastructure you control.

Where your data stays

Papayya does not ingest anything. An item can be an identifier — a claim number, a document key, a row id — and the first step of your agent reads the thing itself from wherever it already lives: your object store, your warehouse, your document management system, your database. Papayya never holds a credential for that source and never connects to it. Your code does, the same way it does today.

So you choose what is recorded, because you choose what the item carries and what each step returns. Send an id and Papayya stores an id, a verdict and a cost. Send the document and it stores the document — sometimes that is what you want, because it is what makes a re-drive reproduce the exact input that failed. It is a decision per workload, and it is one of the things the call is for.

Where it runs

In your cloud. One Linux host with Docker, or the Postgres you already operate. Your items, your outputs and your model-provider keys stay on machines you own — model calls go straight from your workers to your provider, and Papayya is never in the path of one. There is no runtime call home.

What happens after

A one-page fit check by email the same day — six questions about the host, the network and one example input. If it comes back clean, the next call is a screen-share where your own stack comes up, and you are running your own workload that week.

Not ready for a call

The SDK and CLI are on PyPI, the reference documentation is at https://docs.getpapayya.com, and kingsley@getpapayya.com reaches a person. There is also a list on the home page if you would rather hear from us when there is something new.