---
title: "Getting Started"
id: "1732"
type: "page"
slug: "getting-started"
published_at: "2026-09-20T20:56:04+00:00"
modified_at: "2026-09-21T01:36:28+00:00"
url: "https://xedant.com/agents/research/docs/getting-started"
markdown_url: "https://xedant.com/agents/research/docs/getting-started.md"
excerpt: "Xedant Research Agent is a web app for deep online research, planning and documentation. Give…"
---

# Getting Started

[https://xedant.com/agents/research/docs/getting-started.md](https://xedant.com/agents/research/docs/getting-started.md)

Xedant Research Agent is a web app for deep online research, planning and documentation. Give it a topic and it runs dozens of searches, downloads and reads hundreds of pages, pulls out structured data and assembles a verified report into a document library. Xedant Agent works in the background at the same time — its chats are visible and can be managed from the same interface.

## Who it’s for

Research Agent is built for market analysis, planning and documentation — no development skills needed. Unlike Xedant Agent, which looks and works like an IDE (a developer’s code editor), everything here speaks the language of research: topics, search sessions, downloaded pages, reports and plans.

## System requirements

Any Linux host with Docker (a tool that runs an app in its own isolated container): the whole application deploys as one container, the SQLite database is built in, and PostgreSQL — a heavier-duty database for larger setups — is optional. For a step-by-step guide, see the [Installation](/agents/research/install)
 section.

## First sign-in

The first user registers through the web form on the login page: login, password (4 characters or more), name and email. The password is stored as a SHA-256 hash — a one-way fingerprint the original password cannot be recovered from — and the session runs on JWT tokens that keep you signed in. You can also pre-configure the login and password with the `RESEARCH_AGENT_LOGIN` and `RESEARCH_AGENT_PASSWORD` environment variables (`RESEARCH_AGENT_PASSWORD` takes the password’s SHA-256 hash); when they are not set, the registration form creates the first user.

## Home screen

- **Documents** — your research library: a tree of Markdown documents organized by category;
- **Searches** — search sessions and their results;
- **Fetches** — download sessions and the Markdown they fetched;
- **Completions** — the log of LLM calls (requests to the AI model), with token usage and cost;
- **Sessions** — research sessions: the searches, downloads and extractions behind one topic;
- **Chats** — Xedant Agent chats updating in real time; opened in a panel by the button at the bottom of the sidebar;
- **Services** — search providers, download methods and LLM services.

## Your first research

- set up a search provider (its API key — the access password the provider issues you) and an LLM service in the Services section;
- give the agent a research topic — it will run the searches, download the pages and analyze them;
- watch the progress: every operation shows a status and an estimated completion time;
- read the finished report in the Documents library — together with the search sessions and the source pages.

It pays to prepare several topics in advance: put them into the prompt queue — the agent will work through the tasks one after another on its own (see “[Prompt Queue](/agents/research/docs/prompts-queue)
“). A long task doesn’t have to be typed either — you can dictate it (“[Voice Input](/agents/research/docs/speech)
“).

## Interface

The interface language switches between English and Russian in the settings, and the theme between dark and light. Research events come with sound cues — you can hear how the work is going even when the tab is in the background.

## What’s next

How deep research works is covered in the [Online Research Skill](/agents/research/docs/online-research)
 section. Searching and downloading are covered in [Search](/agents/research/docs/search)
 and [Fetching Pages](/agents/research/docs/fetch)
, and data extraction in [Data Extraction](/agents/research/docs/extract)
. Working with documents is described in the [Research Library](/agents/research/docs/researches)
.

[← Back to documentation](/agents/research/docs)