Beyond vectors: Postgres for Production AI Agents
Presented by:
Gwen Shapira
Gwen is a co-founder and CPO of Nile (thenile.dev) where she and the team are building distributed Postgres for multi-tenant applications. She has 20+ years of experience working with code and customers to build reliable and scalable data architectures. Prior to Nile, she was head of Cloud Native Kafka engineering org at Confluent. Gwen is a committer to Apache Kafka, author of “Kafka - the Definitive Guide” and "Hadoop Application Architectures". You can find her speaking at tech conferences or talking data at the SaaS Developer Community.
No video of the event yet, sorry!
AI agents are all the hype now and the key to building a production-grade agent is to make sure the model is backed by production-grade data. Postgres, as a mature, secure and fully-ACID relational database with a large extension ecosystem, is a great fit as the backbone of production-grade agents.
In this talk, we’ll walk together through building an issue triage agent on Postgres. We’ll share large number of patterns, from basic SQL to advanced SQL to various extensions in order to provide language models with relevant data. Then, we’ll explore agentic patterns, where we teach AI agents how to access the data they need on their own.
You'll walk away with practical tips for building AI agents on Postgres. We'll cover key implementation aspects, including data modeling strategies, performance tuning for large datasets, and integrating AI within existing enterprise data ecosystems. Join this session to discover how to streamline your AI architecture, reduce operational overhead, and ground AI in your business facts with PostgreSQL.
- Date:
- Duration:
- 50 min
- Room:
- Conference:
- Postgres Conference: 2026
- Language:
- Track:
- Dev
- Difficulty:
- Easy