onshore
Use cases / Teams building chatbots and copilots

Ship the chatbot. Keep the BVNs.

Models hosted abroad are often the best tools you have, and customer messages are full of identifiers. The gateway lets you use both, with one change to your base URL.

What changes
Prompts
Raw customer messages go to the provider
Identifiers are tokenized first
Replies
No way to refer to the real value
Tokens are restored before your app sees them
Streaming
Filtering often means giving it up
Replies still stream
Oversight
No record of what was sent
Counts by data type and destination
What you'd use
Questions
Which models work?+

Any that speak the OpenAI-compatible API.

Will answers get worse?+

Tokens keep their type, so the model still knows it's a BVN. Test it on your own prompts.

Does it catch Pidgin?+

Accuracy on Pidgin has not been measured yet, so test it on your own messages. You can add your own cue words.

Start with one leak.

Tell us which flow worries you most. We'll show you what it would take to keep it onshore.