Yandex Cloud
Search
Contact UsTry it for free
  • Customer Stories
  • Documentation
  • Blog
  • All Services
  • System Status
  • Marketplace
    • Featured
    • Infrastructure & Network
    • Data Platform
    • AI for business
    • Security
    • DevOps tools
    • Serverless
    • Monitoring & Resources
  • All Solutions
    • By industry
    • By use case
    • Economics and Pricing
    • Security
    • Technical Support
    • Start testing with double trial credits
    • Cloud credits to scale your IT product
    • Gateway to Russia
    • Cloud for Startups
    • Center for Technologies and Society
    • Yandex Cloud Partner program
    • Price calculator
    • Pricing plans
  • Customer Stories
  • Documentation
  • Blog
© 2026 Direct Cursus Technology L.L.C.
Yandex AI Studio
  • About Yandex AI Studio
  • Getting started with Model Gallery
    • Overview of AI agents
    • Voice agents
    • Text-based agents
  • Yandex Workflows
  • Switching from the AI Assistant API to Responses API
  • Compatibility with OpenAI
  • Quotas and limits
  • Pricing policy
  • Access management
  • Audit Trails events
  • Public materials
  • Release notes
  • Terms and definitions

In this article:

  • Text-based agent tools
  • File Search Tool
  • Web Search Tool
  • MCP Tool
  • API for creating text-based agents
  • Methods of creating text-based agents
  • When to use text-based agents
  1. Agent Atelier
  2. Text-based agents

Text-based agents

Written by
Yandex Cloud
Updated at February 3, 2026
  • Text-based agent tools
    • File Search Tool
    • Web Search Tool
    • MCP Tool
  • API for creating text-based agents
  • Methods of creating text-based agents
  • When to use text-based agents

Text-based agents is a Yandex Cloud AI Studio tool for building intelligent applications with context and external integrations. Such agents can interact with the user in text form via chat, forms, APIs, and other application interfaces.

With text-based agents, you can create simple chatbots, advanced intelligent support systems, search and analysis interfaces, and automate your business processes.

AI Studio text-based agents have the following capabilities:

  • Maintaining a dialog based on chat history and context.
  • Response generation in prescribed format, data structuring.
  • Automatic invocation of tools for information search or actions.
  • Working with organization's documents and internal data.
  • Web search.
  • Use of external APIs via MCP servers.
  • State and memory preservation between requests.

Text-based agent toolsText-based agent tools

Text-based agents can automatically invoke tools to enhance their capabilities.

File Search ToolFile Search Tool

The File Search tool implements RAG (Retrieval Augmented Generation) scenarios and allows the agent to search for information in uploaded documents and knowledge bases.

Use this tool to:

  • Upload documents via the management console, Files API, or Vector Store API.
  • Create a search index based on the uploaded data.
  • Use the found fragments in the agent's responses.

Search indexes store the information in vector form for semantic search through the content of the documents.

Web Search ToolWeb Search Tool

The Web Search tool allows the agent to get relevant information from the internet using the Yandex search base. This enriches the outputs with up-to-date data and facts pertaining to your request.

Use this tool to:

  • Name up to 5 domains for your search or use global search.
  • Limit the search region.
  • Limit search results to manage the completeness and level of detail of the output and the spending of tokens.

MCP ToolMCP Tool

The MCP Tool connects text-based agents to third-party APIs via MCP servers.

Use this tool to:

  • Configure connections to external services and tools.
  • Manage MCP server configurations.
  • Monitor connection status.

API for creating text-based agentsAPI for creating text-based agents

For text-based agent development, AI Studio uses Responses API, an OpenAI-compatible API optimized for text-based scenarios. With Responses API, you work with models, tools, and agent memory from the same interface.

Main Responses API features:

  • Generation of context-aware text responses.
  • Automatic tool invocation.
  • Support for RAG scenarios for local data and web search.
  • Formatted and structured responses.
  • Interfacing with any available AI Studio model.

Responses API is suitable for most text-based agent scenarios and is the recommended API for text-based agents.

Methods of creating text-based agentsMethods of creating text-based agents

In AI Studio, you can create text-based agents in several ways:

  • In Agent Atelier, for experiments and prototyping.
  • In Responses API, for software integration into applications.
  • In Yandex Workflows, for building complex scripts in low-code format.
  • Via open-source frameworks compatible with the OpenAI API, such as the OpenAI SDK, LangChain, or LangGraph.

When to use text-based agentsWhen to use text-based agents

Text-based agents will suit many scenarios where:

  • Precise wording and logic make a good response.
  • The task involves working with documents and knowledge bases.
  • You are looking for structured data in the output.
  • Text interfaces or APIs are used.
  • No real-time audio processing is required.

Was the article helpful?

Previous
Voice agents
Next
AI Search overview
© 2026 Direct Cursus Technology L.L.C.