NLX's Generative AI Principles

NLX is relentlessly focused on building a world-class conversational AI platform designed for the enterprise. When incorporating LLMs into our Conversational AI, we follow a set of guidelines to help leverage the very best of the generative AI capabilities, while still maintaining enterprise standards.

Andrei Papancea

08/22/2023

NLX is relentlessly focused on building a world-class conversational AI platform designed for the enterprise. To be at the forefront of embedding generative AI inside our platform has meant focusing our resources on building the most flexible architecture possible with no compromises on security and compliance.

When incorporating LLMs into our Conversational AI, we follow a set of guidelines to help leverage the very best of the generative AI capabilities, while still maintaining enterprise standards.

  • Scalability and Choice even over Walled Gardens: We’ve chosen to integrate or partner directly with other providers who are focused on their own domain so any of our customers can work with their preferred vendors to build a best-in-class ecosystem that meets their objectives. We believe it's important to offer a wide variety of options to serve our enterprise customers' needs, which is why NLX offers pre-built integrations with Amazon Bedrock, Cohere, OpenAI, and others.
  • Practicality even over Hype: Sure, doing something just because you can is cool, but it can eat up a lot of valuable time and effort better spent on improving customer experience. That’s why we’re focused on bot-building productivity and LLM integrations for dynamic QnA and conversational use. Our features result in time, money, and effort saved for you and your team.
  • Build From Ground Truth even over Opinion: It’s rarely the case for enterprises that customer data is easy to access, derive insight from, and act on in a short period of time. NLX’s conversational and generative AI capabilities can now help cluster real-time and past data through zero-shot mapping, allowing brands to identify gaps and areas of improvement based on fact, not thought.
  • Guardrails and Safety even over Open Response: We’re exploring an array of ways to contain generative responses to tightly defined parameters for the enterprise. Unconstrained, LLMs can present a huge risk to brands… more on that here. 
NLX CEO Andrei Papancea shares the company's Generative AI Prinicples! Watch now.

Our guidelines continue to grow as we innovate and experiment, but these are just a few we are focusing on right now based on recent findings and what our customers are looking for. If you’re interested in learning more about NLX’s conversational and generative AI capabilities, please reach out to us via the contact us tab.

Andrei Papancea

Andrei is our CEO and swiss-army knife for all things natural language-related.

He built the Natural Language Understanding platform for American Express, processing millions of conversations across AmEx’s main servicing channels.

As Director of Engineering, he deployed AWS across the business units of Argo Group, a publicly traded US company, and successfully passed the implementation through a technical audit (30+ AWS accounts managed).

He teaches graduate lectures on Cloud Computing and Big Data at Columbia University.

He holds a M.S. in Computer Science from Columbia University.