How Conveyor utilizes LLMs

Conveyor uses OpenAI, Anthropic , and Google to power searches in trust portals and to help vendors respond to questionnaires. This includes a multi-step AI flow for extracting relevant information from knowledge sources as well as incoming questionnaires.

We have intentionally designed and built ConveyorAI with security and privacy as our guiding principles. We are operating under specific guidelines when it comes to generative AI:

• Conveyor does not store Customer Content with any third-party LLMs providers. We use ephemeral API requests.
• Conveyor does not store Customer Content with any third-party LLMs providers. We use ephemeral API requests. Conveyor has entered into Zero Data Retention agreements with LLM providers OpenAI and Anthropic.
• For steps in our processing flow that use Google LLMs, there is temporary retention of data for abuse monitoring as outlined here: https://ai.google.dev/gemini-api/docs/usage-policies
• We do not allow training of third-party LLMs using Customer Content. Third party LLM providers are contractually prohibited from using Customer Content for their own purposes.
• We only use anonymized and aggregated data when it comes to improving our ConveyorAI algorithms.

All calls to LLM provider APIs are server-to-server, meaning no client IP addresses are sent to model providers.

Conveyor has an agreements in place with LLM providers laying out the requirements for the use and confidentiality of the processed data.

All "learning" involves automated curation of customer-specific answers into that customer's specific Conveyor knowledge graph. No customer-specific answers ever go back into training customer-wide models.

Additional resources are made available to customer's in our Trust Center .

📘

If you have any questions

Please don't hesitate to contact [email protected] if you have additional questions. We value transparency in these matters.