CloosphereAll Your AI, Securely Managed in One Place. Product · Agents & flows Connect internal data and business tools,
Connect internal data and business tools,
and run critical actions only after approval
The agent picks the resources a request needs from the Knowledge Base, databases, the glossary, and external tools, and combines them. It asks the user to confirm when it needs more information, and actions that change data or run external systems are carried out only after user approval. Results can be delivered as document files such as PowerPoint, Word, and Excel.
Knowledge Base, DBs, glossary, and external tools TOOLS
Approval card before any data change APPROVE
Results as PPT, Word, or Excel files FILE
Three challenges to solve before AI agents can do real work
Agents need your internal context and business rules
A general-purpose LLM alone can't fully reflect your organization's documents, data structures, terminology, and procedures. Connect the Knowledge Base, databases, the glossary, and MCP tools to an agent to apply your internal data and business context.
Answers need to become real work output
Generate PowerPoint, Word, and Excel files, or turn results into Google Docs, Sheets, and Slides — without copying the conversation into a document again.
Data changes and external actions need approval
Actions that change state, such as sending email or modifying data, show their target and impact right before they run and wait for user approval.
Building, connecting, and running agents
AI chat
- Chat with any of several organization-approved LLMs.
- File attachments, SharePoint document attachments, voice input, image generation.
- Sources are shown as numbered chips, and only the sources actually cited appear. Web search sources are marked with the site icon.
- Suggests follow-up questions after each answer.
Agents
- Connected resources: Connect a Knowledge Base, database, glossary, Knowledge Graph, tools, and skills to each agent individually.
- Capabilities: For each agent, set web search, image generation, Gmail, Calendar, and Drive to hidden, on by default, or off by default — deciding what appears in chat and what users can switch themselves. Document generation (PPT · Word · Excel) is also enabled per agent.
- Clarifying questions and approval: If information is missing, it asks with a set of options; write actions are confirmed with an approval card before running.
- Answer templates: Register multiple templates and it answers using the one that fits the question.
- Rules: Rules registered on an agent are applied consistently to its answers and actions.
- Multi-step requests: Plans out the steps first, and won't report completion if a step is missing.
- Prompt version control: Every save keeps a version you can compare and restore.
Flows
- Connect multiple agents and logic with a no-code visual builder.
- Node families: Agent (agent · model · supervisor), Logic · data (condition · router · merge · transform · loop · subflow), and Control · safety (approval gate · guardrail).
- Agent nodes use the exact agents you've already built in the workspace.
- Run a draft instantly with Test Run and follow progress node by node in the run history. Version control is supported.
Multi-agent
- Turn a workspace agent into a supervisor and it sends each question to the sub-agent whose domain fits, then combines the results into a single answer.
- Each sub-agent answers with the model, knowledge, and tools connected to it, and you can follow each sub-agent's progress in the reasoning panel and traces.
- Structure view: Add and edit sub-agents from the structure view in the agent editor. Calls, tokens, and latency per sub-agent are aggregated from traces.
- Operational controls: Sub-agents the user can't access or that are over their usage limit are left out of the run, and when an admin turns the feature off, supervisors run as normal agents.
Skills
- Register a bundle of scripts as a skill and connect it to an agent. The skill editor can draft one for you with AI.
- Skill file changes are automatically versioned and can be rolled back.
Document generation
- Ask in a conversation and it actually generates PPT, Word, and Excel files.
- Once an admin registers your company's master template, it fills the cover, duplicates body slides, and adds data sheets to match your internal format.
- Edits an attached Excel file cell by cell, row by row, column by column, or sheet by sheet, keeping formulas and formatting intact.
- Creates and edits Docs, Sheets, and Slides in Google Drive. When it's done, a completion card with the title and link stays in the conversation.
Tool connections
- MCP: Connect with an API key, a Bearer token, OAuth, or Cloosphere SSO token passthrough, or without authentication. Choose, tool by tool, which of the server's tools users can see. For each connection, choose whether tool definitions are exposed as-is or routed through a selector.
- OpenAPI: Register your internal API spec as a tool.
- Automatic read/write classification: OpenAPI and MCP tools are automatically classified as read or write, and write tools never run without approval. The classification can be changed per tool.
- Google Workspace: Search and compose across Gmail, Calendar, and Drive in natural language. Features without connection permission stay hidden, and every send is recorded in the Google Workspace send log. Admins turn the integration on or off.
Scheduled runs
- Run an agent task at a set time. Scheduled runs can also use web search and Google Workspace lookups, and attach sources to the result.
- Scheduled runs are shared with read or write permission, and always execute with the creator's permissions — so sharing never escalates access.
Channels
- Web app: Rebrand with your own logo, favicon, and splash screen to run as an internal service.
- Microsoft Teams bot: Pick an agent and chat with it right inside a Teams conversation. Set up and deploy it from the admin screen.
- Embed widget: Add it to an internal portal or groupware with a single script tag. Bubble, side panel, bottom panel, inline, or full-screen display; color, size, and icon can be customized; SSO token exchange or guest mode; allowed domains can be restricted. The agent can even fill in a form or click a button on the page the user is looking at.
Chat, agent editing, multi-agent, skill, document generation, and tool connection screens
One question goes to two models at once, and the answers are laid out side by side.
Related integrations
- LLM connection types (6 + OpenAI-compatible) → Integration specs · LLM
- Tools · protocols → Integration specs · Tools
- Voice · image generation → Integration specs · Voice · Image
Flows, the embed widget, document templates, and branding are included from the Professional tier; tools and image generation are included from the Standard tier. Marketplace skills are a separate add-on. → Pricing · licensing
Related updates
1.7.0 2026-11
Agents Multi-agent supervisor
1.7.0 2026-11
Agents Agent operations monitoring
1.7.0 2026-11
Tools Azure OpenAI web search support
See an agent working with your own documents and tools
We set up a demo environment based on your deployment method, integration scope, and governance requirements.