AI-powered enterprise search with semantic understanding and natural language.
What is Agent Search?
Agent Search, formerly Vertex AI Search, is Google’s solution for AI-powered enterprise search within the Gemini Enterprise Agent Platform. The service goes beyond simple keyword search and understands the meaning of search queries in natural language. This delivers more relevant results even when exact search terms do not appear in documents. The technology is based on Google’s foundation models and years of search experience.
The service automatically indexes various data sources: Cloud Storage buckets, BigQuery tables, websites, and unstructured documents such as PDFs, Word files, and HTML pages. Indexing extracts content, creates embeddings, and builds a semantic search index that understands natural language queries.
As a RAG backend (Retrieval-Augmented Generation), Agent Search is an important foundation for AI assistants, chatbots, and agents, for example in combination with Agent Studio or RAG Engine. The service delivers relevant documents and text passages that serve as context for generated answers. This reduces hallucinations and ensures answers are based on enterprise data.
Core Features
- Semantic search: Natural language understanding for more relevant results beyond keyword matching
- Multi-source indexing: Automatic indexing of Cloud Storage, BigQuery, websites, and documents
- RAG integration: Retrieval-Augmented Generation as a backend for LLM and agent applications
- Personalization: Context-aware search results based on user behavior and roles
Typical Use Cases
Knowledge Management and Internal Search
Organizations use Agent Search as a central search platform for internal documentation, wikis, policies, and training materials. Employees find information through natural language queries without needing to know exact search terms.
AI Assistants with Enterprise Knowledge
Agent Search serves as a RAG backend for AI assistants that access enterprise data. The chatbot answers questions based on current documents and provides source citations for generated answers.
Benefits
- Semantic understanding instead of pure keyword matching
- Quick setup without manual index configuration
- Reduced hallucinations in LLM and agent applications through RAG
- Automatically scales with data volume
Integration with innFactory
As a certified Google Cloud partner, innFactory supports you with Agent Search: designing AI search solutions, data source integration, RAG pipeline development, and building AI assistants with enterprise knowledge.
Typical Use Cases
Frequently Asked Questions
What is Agent Search (formerly Vertex AI Search)?
Agent Search is an AI-powered search service within the Gemini Enterprise Agent Platform that understands natural language and delivers semantic search results across enterprise data. It combines classic search technology with large language models for more precise, contextual results. Former names of the product include Vertex AI Search, Enterprise Search, and Generative AI App Builder.
Which data sources are supported?
Agent Search supports data sources including Cloud Storage, BigQuery, websites, and unstructured documents such as PDF, Word, and HTML. Data sources are automatically indexed and prepared for search.
How does integration with LLMs and agents work?
Agent Search can serve as a Retrieval-Augmented Generation (RAG) backend for LLM and agent applications, for example in combination with Agent Studio or RAG Engine. The service delivers relevant documents and context used as the basis for AI-generated answers, reducing hallucinations.
What was Vertex AI Search and how does it relate to Agent Search?
Vertex AI Search was the product's name before Google moved Vertex AI into the Gemini Enterprise Agent Platform as part of the Google Cloud Next '26 rebranding wave. The underlying Discovery Engine API and core functionality remain unchanged.
Note: All product information on this page has been compiled with care, but is provided without guarantee and may be outdated or incomplete. Cloud services evolve rapidly — features, pricing, SLAs, and availability change frequently. Authoritative and up-to-date information can only be found on the official product page of Google Cloud (official documentation). This page does not represent an offer by Google Cloud.
