Ariadne User Documentation
Documentation for how to use the Ariadne platform
- a2a-agentsAriadne speaks the **Agent2Agent (A2A) protocol**, an open standard (governed by the Linux Foundation) for letting AI agents from different vendors work togethe…
- account-and-organisationThis guide covers user profile management, API access, organisations, and subscriptions. Go to **User Menu → My Profile** to manage your personal details. From…
- agents**Agents** are the AI personas at the heart of Ariadne. Each agent has its own system prompt, tool collection, reasoning settings, and optionally connected know…
- briefingsThe **Briefings** feature — *The Ariadne Daily* — delivers personalised AI-generated briefings on the topics you care about. Think of it as a custom newsletter…
- chat-and-conversationsConversations are the core interaction model in Ariadne. Every message you send to an agent — and every reply — is stored in a conversation, giving you a persis…
- code-modeThe **Code** conversation mode turns Ariadne into a full coding assistant with direct access to real files, terminals, and development tools — not just a chat i…
- console-appThe **Ariadne Console** is a command-line client that brings the full power of Ariadne to your terminal. It supports interactive and headless modes, has direct…
- deep-research**Deep Research** takes one question and produces a cited report. It decides for itself what to look for, searches, picks which sources are worth reading, reads…
- desktop-appThe **Ariadne Desktop App** is a native Windows application that provides a rich, full-featured Ariadne experience without needing a browser. It offers the same…
- devopsAriadne can see and act on the infrastructure your code actually runs on — Azure, AWS, Portainer, or a Docker host of your own — through a single fenced, audite…
- email-and-calendarAriadne can connect to your email and calendar accounts, giving agents the ability to read your messages and upcoming events — and optionally send emails on you…
- getting-startedAriadne is a continuous cognition platform that lets you work with AI agents across conversations, memory, tools, and integrations. This guide explains the core…
- goals-and-schedules**Goals** and **Schedules** let you set agents to work autonomously — either pursuing long-term objectives over time, or running on a fixed timetable. A **goal*…
- guard-rails**Guard Rails** let you define safety and content governance rules that Ariadne enforces on agent behaviour. Guard rails use an LLM classifier to evaluate agent…
- how-ariadne-comparesA capability comparison between Ariadne and the two leading hosted AI platforms: **Anthropic Claude** (Claude.ai, Cowork, Claude Code, Projects, Skills, MCP) an…
- knowledgeThe **Knowledge** section lets you build structured, persistent information stores that agents can draw upon during conversations. It is separate from conversat…
- mcp-serversAriadne has a two-way relationship with the [Model Context Protocol](https://modelcontextprotocol.io) (MCP): 1. **As a client** — Ariadne connects to external M…
- notesThe **Notes** feature gives you a personal, structured markdown workspace that is fully accessible to Ariadne's AI agents. Notes are organised in folders, suppo…
- personas-and-web-chat-widget**Personas** let you create named, public-facing AI assistants that can be embedded on any website as a chat widget — no login required for end users. This is i…
- projectsA **project** is one unit of work — a product, a client engagement, a piece of research, a house move — gathered into a single place. Conversations, tasks, docu…
- READMEWelcome to the Ariadne documentation. Ariadne is a continuous cognition platform that brings together AI agents, memory, tools, and integrations into a single c…
- summarisationThe **Summarisation** feature lets you extract the key information from a wide range of content types — web pages, videos, audio recordings, YouTube links, and…
- supportAriadne can investigate a support ticket against real infrastructure — correlating recent deployments, metric breaches, restarts and log errors into a ranked hy…
- testingAriadne agents can register a test suite for a project, run it, and report structured results back in chat — without you leaving the conversation to check a CI…
- visualiseThe **Visualise** feature lets you create and manage **3D scene objects** — a visual space where AI agents can place, update, and remove objects to build spatia…
- web-spiderThe **Web Spider** lets you crawl a website and automatically index its content so that Ariadne's agents can search and reference it. This is ideal for building…
- website-automationThe **Website Automation** feature lets you record interactions with a website and replay them on demand — either manually or triggered by an agent. This is use…
- whiteboardThe **Whiteboard** feature provides a collaborative visual workspace where you and your team can sketch ideas, create diagrams, and brainstorm — with AI assista…
- workThe **Work** feature provides a **kanban-style project and task management** board, allowing you and your team to track work items through a pipeline of stages…
- workflows-and-webhooks**Workflows** and **Webhooks** provide powerful automation and integration capabilities — letting you build multi-step automated processes and connect Ariadne t…