From company context to work that gets done.

One workspace for conversations, capable agents and recurring tasks. Connected to your Knowledgebase, with models, tools and permissions managed in one place.

Familiar chat. Context that belongs to your business.

Ask a question, attach a document or image, and research the web. Choose an approved model for the task while your company knowledge stays connected through permission-aware access.

  • Conversations, projects and files
  • Web search and model-supported image inputs
  • Sources and usable document results
Real CogLake chat with a synthetic customer briefing
CogLake AI Workspace · Example with fictional content

Give an objective. Follow the work.

Let an agent research, use tools, work with files or run code in an isolated environment. Inspect its work log and approve actions when your policy requires it.

  • Research, browser use and isolated execution
  • Tools, MCPs and specialized skills
  • Clear approvals and traceable results
From knowledge to workExample workflow
  1. Brief

    Summarize the changes to our product offering and prepare a customer briefing.

  2. Context

    Read authorized product documents and current notes from the wiki.

  3. Result

    Create a sourced briefing and make it available for review.

Source permissions · Tool policies · Approvals

A working relationship, not a one-off prompt.

Create a dedicated agent with instructions, memory and its own workspace. Continue the conversation, schedule routines and return to its saved progress.

  • Persistent workspace and memory
  • Routines, checkpoints and task continuity
  • The same central access and model policies
A personal agent’s working context

Agent workspace

Instructions

Saved progress

Files and results

Continue the task instead of rebuilding the context every time.

The right task. At the right time.

Choose a trigger, give clear instructions and select the skills or services the agent may use. Run it manually to test, then inspect each execution in the run history.

  • Schedules, intervals and one-time runs
  • Webhooks, HTTP and connected events
  • Manual tests, pause controls and run history
A recurring workflow
  1. Every weekday · 08:00Europe/Berlin
  2. Prepare a product briefingKnowledge sources + approved tools
  3. Review the resultApproval according to policy

Give your agent the right tools for the job.

Discover services and skills from connected libraries. Add personal resources or use centrally configured company connections without repeating the same setup for every employee.

  • Searchable MCP and skill libraries
  • Personal and company-managed connections
  • Permissions and approval policies before actions
EU control foundation
Identity & permissions01
Audit & provenance02
Residency & recovery03

Your models. Your operating choices.

Use centrally provided models, bring your own API keys or connect your own inference. Administrators decide which providers and models are available to each organization.

  • OpenRouter, OpenAI, Anthropic and Gemini
  • Ollama and vLLM for your own inference
  • Provider controls, usage visibility and BYOK policy
Model providers
ChatGPT
Claude
Gemini
Mistral AI
Governed contextOne policy boundary
Interfaces
Search
AI agents
MCP & API
Local models

Keep the work. Review it where it happens.

Open documents, spreadsheets, PDFs, images and code beside the conversation. Download the result or add an authorized artifact to the Knowledgebase.

  • Office, PDF, tables, media and code previews
  • Static HTML previews with restricted execution
  • Downloads and permission-checked knowledge handoff
Results you can keep working with
BriefingDOCX · PDF
AnalysisCSV · XLSX
Code and HTMLStatic preview

Review, download or add to the Knowledgebase with the required permissions.

Frequently asked questions

How do chat, agents and automations differ?

Chat is for direct conversations. Agent Mode handles multi-step tasks. A personal agent retains its workspace and memory for ongoing work. Automations start defined tasks on a schedule or event.

Can employees use their own providers?

If company policy allows it, employees can add personal API keys and resources. Administrators can restrict provider access and offer centrally managed connections instead.

Does an agent act without asking?

That depends on the selected approval mode, allowed and denied actions, and organization policies. Required approvals appear in the conversation; central restrictions cannot be bypassed by the user mode.

Is model usage included in Knowledgebase pricing?

The AI Workspace is an additional product. Its commercial scope and model usage are agreed separately. BYOK usage is billed by the connected provider under your own agreement.

Start with your use case.

See sources, access controls and a relevant workflow together, not as an isolated list of features.

Book a walkthrough