> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developers.alephant.io/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developers.alephant.io/_mcp/server.

# AIvis Overview

> Understand AIvis, its core capabilities, and the first configuration steps for a deployment.

AIvis is a privately deployed enterprise AI workspace. It brings chat, enterprise knowledge, model configuration, Agents, Actions, scheduled tasks, and organization governance into one controlled surface while keeping knowledge, indexes, files, credentials, task history, and audit data inside the enterprise network, cloud account, or data-center boundary.

<title id="aivis-overview-title-en">
  AIvis Private Deployment and Data Privacy Map
</title>

<desc id="aivis-overview-desc-en">
  Shows AIvis as a private enterprise deployment that keeps knowledge, files, indexes, credentials, task history, and audit data inside the enterprise-controlled boundary and sends only authorized minimum context to external models or tools.
</desc>

<defs>
  <linearGradient id="aivis-overview-bg-en" x1="0" y1="0" x2="1" y2="1" />

  <filter id="aivis-overview-shadow-en" x="-20%" y="-20%" width="140%" height="140%" />

  <path d="M0 0 L10 5 L0 10z" fill="#60a5fa" />
</defs>

<rect width="1200" height="1420" rx="28" fill="url(#aivis-overview-bg-en)" />

<text x="56" y="72">
  AIvis Private Deployment and Data Privacy Map
</text>

<text x="56" y="108">
  Designed so enterprise data stays in your environment while models, tools, and agents receive minimum authorized context
</text>

<rect x="56" y="155" width="1088" height="420" rx="30" />

<text x="96" y="205">
  1\. Enterprise private deployment boundary
</text>

<rect x="96" y="240" width="310" height="135" rx="22" />

<text x="132" y="288">
  AIvis Web / API
</text>

<text x="132" y="326">
  deployed in your environment
</text>

<text x="132" y="354">
  identity and workspace checks
</text>

<rect x="445" y="240" width="310" height="135" rx="22" />

<text x="481" y="288">
  Enterprise data plane
</text>

<text x="481" y="326">
  files, database, indexes
</text>

<text x="481" y="354">
  knowledge and history retained
</text>

<rect x="794" y="240" width="310" height="135" rx="22" />

<text x="830" y="288">
  Background services
</text>

<text x="830" y="326">
  connectors, indexing, schedules
</text>

<text x="830" y="354">
  runs are traceable
</text>

<rect x="96" y="415" width="310" height="115" rx="22" />

<text x="132" y="462">
  Credential custody
</text>

<text x="132" y="500">
  secrets do not enter prompts
</text>

<rect x="445" y="415" width="310" height="115" rx="22" />

<text x="481" y="462">
  Permission filtering
</text>

<text x="481" y="500">
  user, group, document scope
</text>

<rect x="794" y="415" width="310" height="115" rx="22" />

<text x="830" y="462">
  Audit facts
</text>

<text x="830" y="500">
  runtime facts, not secret content
</text>

<path d="M600 575 V645" />

<rect x="56" y="645" width="1088" height="385" rx="28" />

<text x="96" y="695">
  2\. AI capabilities inside the boundary
</text>

<rect x="96" y="730" width="310" height="135" rx="22" />

<text x="132" y="778">
  Chat, search, multimodal
</text>

<text x="132" y="816">
  unified user entry
</text>

<text x="132" y="844">
  text, web, image, voice, code
</text>

<rect x="445" y="730" width="310" height="135" rx="22" />

<text x="481" y="778">
  Model providers
</text>

<text x="481" y="816">
  admin-configured access
</text>

<text x="481" y="844">
  minimum approved context only
</text>

<rect x="794" y="730" width="310" height="135" rx="22" />

<text x="830" y="778">
  Knowledge
</text>

<text x="830" y="816">
  connectors, indexes, sets
</text>

<text x="830" y="844">
  answers use authorized chunks
</text>

<rect x="270" y="895" width="310" height="100" rx="22" />

<text x="306" y="943">
  Agents and Actions
</text>

<text x="306" y="972">
  MCP / OpenAPI checked before calls
</text>

<rect x="620" y="895" width="310" height="100" rx="22" />

<text x="656" y="943">
  Scheduled Tasks
</text>

<text x="656" y="972">
  run with creator permissions and audit trail
</text>

<path d="M600 1030 V1100" />

<rect x="56" y="1100" width="1088" height="245" rx="28" />

<text x="96" y="1150">
  3\. Enterprise privacy and governance posture
</text>

<rect x="96" y="1185" width="310" height="105" rx="22" />

<text x="132" y="1230">
  Data stays in boundary
</text>

<text x="132" y="1264">
  external services receive minimum context only
</text>

<rect x="445" y="1185" width="310" height="105" rx="22" />

<text x="481" y="1230">
  Least privilege
</text>

<text x="481" y="1264">
  prompts cannot expand access
</text>

<rect x="794" y="1185" width="310" height="105" rx="22" />

<text x="830" y="1230">
  Fail closed
</text>

<text x="830" y="1264">
  missing identity or ambiguous config is denied
</text>

<rect x="90" y="1360" width="1020" height="40" rx="16" />

<text x="126" y="1386">
  For private enterprise deployments: knowledge, connectors, indexes, files, audit records, and scheduled run history stay under enterprise control.
</text>

## What AIvis is

AIvis is the unified entry point for teams using generative AI. Users can chat with approved models, knowledge, and Agents; administrators configure model access, connect knowledge sources, publish Agents, manage roles and groups, and control which integrations or tools are available.

For enterprise deployments, the goal is not to let models access data without boundaries. AIvis separates models, knowledge, tools, and people into reviewable configuration surfaces. Each capability must be enabled by administrators, then applied through roles, groups, Agent configuration, and runtime authorization.

In private deployments, AIvis emphasizes data residency and minimum disclosure by default. Enterprise knowledge bases, indexes, files, conversations, task history, audit records, and connector configuration are held by the enterprise deployment. When an external model or tool is used, AIvis sends only the minimum authorized context generated for that request, not the full knowledge base, raw secrets, or unauthorized documents.

## Quickstart

| Path                        | Use when                                                                                              | Next step                                                   |
| --------------------------- | ----------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- |
| Local or private deployment | You need to validate deployment form, ports, images, and base services.                               | Read [Deployment Quickstart](/aivis/deployment-quickstart). |
| Production planning         | You need to decide whether to enable connectors, indexing, knowledge retrieval, and background jobs.  | Read [Deployment Modes](/aivis/deployment-modes).           |
| Administrator setup         | You already have a deployment and need the first administrator, roles, and responsibility boundaries. | Read [Admin Panel & Roles](/aivis/admin-panel-and-roles).   |
| Agent launch                | You need to combine models, knowledge, and Actions into reusable assistants.                          | Read [Manage Agents](/aivis/agents/agents).                 |

## Major capabilities

| Capability                  | What it does                                                                                                                                                             |
| --------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Chat                        | Provide a unified chat entry point using administrator-enabled models, knowledge, and capabilities.                                                                      |
| Agents                      | Combine instructions, models, knowledge, and Actions into reusable assistants for business workflows.                                                                    |
| Internal knowledge search   | Index enterprise content from approved connectors and improve responses with retrieval.                                                                                  |
| Web Search                  | Add public external information when the deployment allows it, without mixing it with internal knowledge governance.                                                     |
| Image, video, and voice     | Provide multimodal generation or input/output inside configured model and service boundaries.                                                                            |
| Actions                     | Use MCP Actions or OpenAPI Actions to call approved tools for auditable work.                                                                                            |
| Code Interpreter            | Provide controlled execution for calculation, data processing, and analysis tasks when supported by the deployment.                                                      |
| Scheduled Tasks             | Run approved Agents once or on a recurring schedule and review execution history.                                                                                        |
| Model routing and providers | Manage model credentials, language models, custom inference providers, default models, and generation capabilities.                                                      |
| Privacy Dictionary          | Define organization-specific sensitive entities and decide whether matches are tokenized, generalized, routed locally, blocked, or marked for review before model calls. |
| Governance and audit        | Manage users, groups, roles, usage, identity, security, and connector data boundaries.                                                                                   |

## Why AIvis

AIvis is designed for teams that need AI capabilities inside real enterprise workflows:

* More reliable internal knowledge: use connectors, indexing, document sets, and retrieval settings to ground answers in approved organization knowledge.
* More controlled private deployment: choose deployment modes that match your security, network, data, and compliance requirements.
* Finer-grained configuration: govern models, providers, connectors, Agents, Actions, scheduled tasks, roles, and groups independently.
* Safer Agent execution: Agents can only use saved configuration for models, knowledge, and Actions; they cannot expand access on their own.
* Clear expansion path: start with Lite for chat and Agent validation, then move to Standard when enterprise knowledge retrieval is required.

## Recommended configuration order

1. Confirm the deployment mode: decide whether connectors, OpenSearch, indexing, and RAG are required.
2. Establish administrators and roles: define Admin, Curator, and Global Curator responsibility boundaries.
3. Configure models: add model credentials, enable language models, set the default model, and enable required generation capabilities.
4. Connect knowledge: choose connectors, limit indexing scope, and validate document sets and retrieval.
5. Publish Agents and configure scheduled tasks: combine instructions, models, knowledge, and Actions, then test before sharing or scheduling.
6. Configure the Privacy Dictionary: publish sensitive entity rules for masking, local routing, blocking, and review before model calls.
7. Establish governance: review users, groups, roles, usage, identity, security, and data-flow boundaries.

## Deployment boundaries

Menu visibility and available controls depend on the deployment configuration. Lite mode does not include a vector database; use Standard mode to enable connectors and vector indexing.

Some capabilities are conditional. Craft appears only when the deployment declares it available; Tracing is available only in supported deployment forms; Query History can be disabled or hidden by an administrator; and connectors, indexing, and document sets depend on Standard mode and the relevant background services.

## Next steps

If this is your first deployment, start with [Deployment Quickstart](/aivis/deployment-quickstart). For production rollout, follow [Deployment Modes](/aivis/deployment-modes), [Model Credentials](/aivis/models/model-credentials), [Connectors & Indexing](/aivis/knowledge/connectors), [Agents](/aivis/agents/agents), [Security](/aivis/governance/security), and [Tracing](/aivis/governance/tracing).

For production environments, also review [AIvis Security](/aivis-security/overview) to confirm system architecture, Agent runtime, security strategy, data flows, data storage, and access controls.