Getting Started
What Research is, first sign-in, service setup, and your first research.
Online Research Skill
The deep research pipeline: search, download, extraction, report, verification.
Search
Eleven providers (including Yandex results via JsonSeo), fallbacks, search sessions, relevance filtering.
Fetching Pages
Five fetch methods — from a direct request to an undetectable browser, working around blocks, conversion to Markdown.
Data Extraction
Chunking, batch extraction to TSV/JSON, batches, tokens and cost.
Research Library
The document tree, images and attachments, the editor, source preview, Edit with AI.
Planning & Ideas
Generating ideas, plans, and interfaces for development agents.
Action Research
plan → act → observe → reflect cycles on three levels.
Agent Integration
Agent chats in the interface, calling the agent from a document, the agent API.
Services & Models
Search providers, fetch methods, LLM services, priorities, copying settings.
Prompt Queue
Prepare tasks in advance and the agent works through them on its own: AutoSend, Max active chats, a recurring prompt generator.
Python Scripts
Your own scripts without rebuilds: a custom search source, a custom fetching method, a custom model gateway, Markdown and extraction-row processing.
Voice Input
Dictate a task straight into the agent chat — no typing needed; speech is recognized by the browser or by the configured agent’s engine.