# Three Ways to Use Neon for AI

DevFeed: [Three Ways to Use Neon for AI](<https://devfeed.tech/articles/three-ways-to-use-neon-for-ai-5829.md>)

Original publisher: [Read original article](<https://neon.com/blog/three-ways-to-use-neon-for-ai>)

Author: Carlota Soto

Published: 2025-07-29T16:34:01Z

Content type: article

Language: en

Sources: [Blog -- Neon Docs](<https://devfeed.tech/sources/blog-neon-docs.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Databases](<https://devfeed.tech/topics/databases.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [autoscaling](<https://devfeed.tech/topics/autoscaling.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [benchmarking](<https://devfeed.tech/topics/benchmarking.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>), [SQL](<https://devfeed.tech/topics/sql.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [applications](<https://devfeed.tech/tags/applications.md>), [autoscaling](<https://devfeed.tech/tags/autoscaling.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [building](<https://devfeed.tech/tags/building.md>), [developer-experience](<https://devfeed.tech/tags/developer-experience.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [product](<https://devfeed.tech/tags/product.md>), [search](<https://devfeed.tech/tags/search.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [sql](<https://devfeed.tech/tags/sql.md>)

## AI overview

The article describes three ways developers use Neon for AI workflows: building vector-based applications with pgvector, managing databases through AI-assisted coding tools, and using databases as backends for agents that deploy full-stack applications. It focuses on combining embeddings, semantic search, and RAG with Postgres instead of operating a separate vector database. Neon adds serverless capabilities such as autoscaling, branching for experiments, and multi-project regional deployment to improve cost, performance, latency, isolation, and developer experience.

## Source excerpt

It's not only hype: developers are working with AI every day - both using new AI-powered tools and building their own. At Neon, we're seeing Postgres widely used in three AI workflows: Vector search with pgvector Many AI applications rely on vector embeddings for semantic search,...