INSIDE THE CORE

The model thinks.
AI×9 remembers, connects,
checks and acts.

Nine roles coordinated on the same Core and sharing the same authorized information. Your AI is the interface; behind it, your world stays organized.

ERIC + EIGHT SPECIALISTS

One team.
Shared knowledge.

Select a role to explore it. Eric brings together the specialists’ actual contributions; the routing service handles the assignment of requests.

Nine roles, not nine chats to manage.
The model can change. The Core stays.

ChatGPTClaudeYour model
ONE INTERCHANGEABLE MODEL
KnowledgeMemoryTool LayerPermissions

Eric · Synthesis and verificationCollects the specialists’ actual contributions and turns them into a useful synthesis. The context remains shared.

Interactive architecture diagram

YOUR AI, NOT AN IMPOSED AI

Change models.
Keep your world.

ChatGPT, Claude or other compatible models: choose the connection supported in your environment. The Core retains Knowledge, sources, memory, organization and authorizations.

The connection to your AI

OmniAgents and OmniAgents Business

MCP is the connection between your compatible model and OmniAgents. The conversation stays in your AI, which accesses the Core’s context and authorized tools.

Direct API + integrated Chat

OmniAgents Business only

Adapters connect supported providers to the Business runtime. Capabilities, credentials and limits are defined in the configuration.

Actual compatibility depends on the client and adapter. History held by an external service remains separate from the Core’s memory.

KNOWLEDGE & MEMORY

Knowledge has a structure.

Each layer has a precise function. A product manual does not become a fact about the company; content does not grant permissions.

01

Foundation

Shared methodology and foundational knowledge.

02

Product / App

Versioned application guide: product sections, actions and terms.

03

Preset

Initial context and industry terminology.

04

Role

Skills and responsibilities of specialist roles.

05

Tenant / Organization

Private organizational facts, with origin and authorizations.

06

Live Learning

New knowledge validated from authorized sources. It does not change the model’s weights.

Chat memory · Conversation Memory
Retains messages and context from conversations managed by the Core, with links to the session and request.

Internal memory · Deep Memory
Retains consolidated context with provenance and state, so it can be retrieved in new conversations too. The environment’s data stays yours.

INTERNAL KNOWLEDGE / A GUIDE IN THE CONVERSATION

Your AI knows
OmniAgents too.

Internal Knowledge gives agents clear context about the application: sections, functions, terms and workflows. This lets the model and Eric also act as the assistant guiding you through the app.

01 / KNOWING THE APP

Product Knowledge

A versioned application guide describes the environment, its functions and the available steps.

02 / UNDERSTANDING THE TASK

Context for every agent

Each role uses the knowledge relevant to its task, together with information from your environment.

03 / GUIDING YOU

The model and Eric guide you

They explain where to start, clarify the differences between functions and guide you through the steps of your work.

EXAMPLE / FINDING YOUR WAY AROUND THE APP
“I want to connect Google Photos and use the images in my project. Where do I start?”
  1. Identifies the path. Directs the question toward connecting Google Photos and selecting images.
  2. Explains what you are doing. Distinguishes authorization, importing and the availability of content to agents.
  3. Guides you through your work. Connects the next step to the app’s functions, keeping the decisions in your hands.

Application Knowledge, data from your sources and chat memory remain separate layers. The guide explains how things work; permissions determine which actions can be carried out.

TOOL LAYER

Context meets tools.

The model communicates with the Core through MCP. Connectors, APIs and web tools connect context to authorized operational capabilities. Every action goes through the required checks.

Connection to the model · MCPConnectorAPIWeb SearchWeb Fetch
  1. Origin and identity
  2. Organization and session
  3. Permission and connector status
  4. Check before the action
  5. Provenance and receipt
  6. Return to the request

Checks that are part of the process.
Protected credentials, separate environments, permissions and action history accompany every request. You can distinguish what is complete from what requires verification.

Security and boundaries

WHAT’S BEHIND A REQUEST

You see a conversation.
Behind it, an architecture is at work.

Sources with a history. Memory with a state. Coordinated roles. Actions with permissions and receipts. Every step has a precise responsibility.

Explore the architecture

YOUR EVERYDAY ENTRY POINT

Control is in the conversation.
The dashboard can stay closed.

ChatGPT, Claude or the compatible client you have configured: your request starts there and the result returns there. You don’t need to open OmniAgents to search and prepare. To confirm sending or a change, open the app on your computer.

YOU, IN YOUR AI

Ask.
Search.
Prepare.

ChatGPTClaudeCompatible client
OMNIAGENTS, BEHIND THE CONVERSATION

AI×9

Connected sourcesKnowledge & MemoryAgents and toolsPermissions and verification
IN THE SAME CONVERSATION:Answer and sources. You confirm actions in the OmniAgents app on your computer.

After setup, the dashboard is where you change settings, check the environment and confirm sending and changes. The Core must be active and reachable; capabilities depend on the connection and permissions.

WORK SCENARIOS, BEYOND QUESTIONS

One request.
Multiple sources. A clear path.

From context to decision: here is how you can set up a complete piece of work in the conversation with your AI.

OMNIAGENTS AND BUSINESS
“Read the requests that have arrived since yesterday, compare them with today’s appointments and tell me what needs attention. Prepare a reply to the two most urgent ones, but let me approve them before you send them.”
Gmail and messagesCalendarContactsKnowledge
  1. 01

    Rebuilds the context

    Connects senders, previous conversations, deadlines and appointments.

  2. 02

    Distinguishes priorities

    Separates documented urgency, routine requests and missing information.

  3. 03

    Prepares the work

    Composes drafts using authorized context and keeps sources accessible.

Sending remains pending your confirmation and the connector’s permissions.

The system works on the sources you authorize. Missing information remains explicit.

Your preferences

The choice stays yours.

The site stores a local preference to remember your choice. Optional analytics stay off until you accept them. You can change your choice at any time.

Read the Privacy Policy