Deepak Nair

I research and build AI-native customer experience systems.

I currently work at Google, shipping advertiser-facing AI agents. If you use Google Ads support, I’d love to hear your feedback on how we’re doing.

What I’m working on

• SupportBench: an open benchmark for evaluating AI-native customer support systems.
• Small, reproducible experiments on memory, retrieval, tool use, escalation, and policy adherence.
• Open-source tools that help engineers build support systems customers can trust.

What I believe

• Customer support systems should be evaluated as complete systems, not just language models.
• A useful benchmark is more valuable than a persuasive demo.
• Making AI agents reliable in enterprise settings is hard but possible.
• Model capabilities are often ahead of how reliably we know how to use them.

Writing

• Building the Open Standard for AI-Native Customer Support

About this work

This is an independent research project. Examples use synthetic data or publicly available information.

You can email me at hello@deepnair.ai.