Early Access

How Zokai keeps you in control

Zokai runs wherever you decide: your own hardware, your data centre, the infrastructure provider you trust, or dedicated servers we operate for you in Germany. The AI works through a defined set of capabilities you control, never by clicking through screens. Calculations run in code you can inspect. Every change, run and approval is recorded in a ledger you can verify yourself.

Early Access. Zokai Station is available to selected organisations through commercial pilots. Scope, hosting and support are agreed individually for each pilot.

This page describes how Zokai is designed. The detailed architecture is available under NDA.

Security properties

Isolated storage

Your documents, mail index and databases sit in a layer with no route to the internet

Credentials stay local

API keys and account tokens are stored as encrypted local secrets, never in configuration files, and never sent to us

No telemetry

Zokai doesn't phone home. Outbound traffic only goes to services you connect

Single-tenant

No shared databases or infrastructure between customers, on your premises or hosted

Least privilege

Every component runs with minimal rights and fixed resource limits

You choose where it runs

Your hardware, your data centre, any provider you pick, or managed by us in Germany. No US-parent provider in our software stack; the hosting jurisdiction is your decision

Three modes: what can leave, per mode

You choose the mode for each session. Each mode has its own fixed set of capabilities, so switching mode changes what the AI can reach, not just what it's told.

Air-gapped

The AI can use

Your documents, spreadsheets, notebooks, mail, calendar, tasks and workflows, with a local model

What can leave your infrastructure

Nothing

Private hybrid

The AI can use

Everything in Air-gapped, plus web research, YouTube transcripts and bookmarks

What can leave your infrastructure

Prompts to the cloud model you select. Delegated tasks are masked, and your files aren't uploaded wholesale

Frontier

The AI can use

Everything in Private hybrid, plus GitHub and autonomous developer agents

What can leave your infrastructure

Cloud reasoning, for work you decide is suitable

What the AI can work with

Mail and calendar

Search all mail by meaning, draft replies, find free slots, book meetings. Gmail and Google Calendar today; Microsoft 365 and IMAP in development

Documents

Draft and edit proposals and contracts, cite PDFs, show who wrote what

Spreadsheets

Read and write Excel and CSV, insert real formulas, audit ledgers

Notebooks

Run exact Python and SQL analyses on your data

Search across everything

One question across mail, PDFs, spreadsheets, notes and files

Web research

Multi-source research, YouTube transcripts, bookmark collections (Private hybrid and Frontier)

Automation

Scheduled and event-triggered workflows with approval steps

Code

Repository inspection and developer agents (Frontier)

Built on the open Model Context Protocol (MCP).

How automations stay safe

01

Describe it once, in plain language.

"When the monthly sales report arrives, analyse it, draft the board narrative, build the deck, and wait for my sign-off before anything is sent."

02

Exact analysis, with no AI involved.

The numbers are computed by code, the same way on every run.

03

AI only where it adds value.

One step turns results into board-ready text, and the output is checked against a required format before the workflow continues.

04

Sign-off before anything leaves.

The workflow pauses until a person approves.

  • Tested before it's switched on: a test run replays a past event; reads are real, sends and writes are blocked.
  • Correct steps in plain English: the assistant updates the workflow, checks it, and runs the test again.
✕

Cloud automation tools

Break when APIs change, charge per task, move data to third-party clouds

✕

Screen-clicking AI agents

Fragile, expensive, can act without approval

✓

Zokai workflows

Step-by-step, repeatable, approval gates, run on infrastructure you choose

The audit trail

One record for everything the people and the AI do.

Documents

Every create, edit, rename and delete, with time and source. Full content history is kept, so any earlier version can be restored

Spreadsheets

Every cell change with its previous value and time. Restoring creates a new entry instead of rewriting history

Workflows

Every change to a workflow, every run, and every approval

AI conversations

Prompts and responses, kept as an append-only record

How the record protects itself

  • Entries can be added but not changed or deleted in normal operation.
  • Entries are cryptographically chained, so altering any past entry breaks the chain from that point on.
  • You can run the verification yourself, at any time, on your own infrastructure.

Being hardened (we say this openly)

  • Sealing the per-step details of every workflow run into the chain
  • Ensuring no edit or approval can complete without its record entry
  • Daily anchoring of the record outside the system, for example to your auditor

Every workspace, recorded live

Morning briefing

Recorded live · 2:00
Jump to:

The assistant synthesizes executive priorities and books time blocks into the calendar on a single confirmation.

Cross-search across mail, files and calendar

Recorded live · 1:04
Jump to:

A single query retrieves project budgets, agreements, client emails, and scheduled meetings across connected sources.

Document drafting with change history

Recorded live · 0:50
Jump to:

The assistant restructures a client proposal; the document history shows every change and where it came from.

File search

Recorded live · 0:40
Jump to:

Search across multi-format workspace files with built-in previewers.

Expense audit

Recorded live · 1:40
Jump to:

The assistant audits spreadsheet data: generating formulas, policy disallowance checks, and audit aggregates directly in the sheet.

Monthly sales report workflow

Recorded live · 1:26
Jump to:

End-to-end workflow execution: data analysis, structured narrative, authority gate sign-off, and presentation generation.

Deployment options (commercial pilots)

During Early Access, every deployment option is offered as a commercial pilot. Hosting, scope and support are agreed for each pilot.

Your hardware (air-gapped possible)

Maximum control; nothing has to leave the building

Your data centre or chosen provider

Runs on the infrastructure and in the jurisdiction you already trust

Managed by Zokai in Germany

Dedicated single-tenant servers, operated for you

Zokai is containerised and runs on standard Linux servers. Air-gapped mode runs current open models (around 30B parameters) locally. A typical setup is a server with an NVIDIA GPU with at least 24 GB of memory; 48 GB is recommended for teams and long documents. Apple Silicon workstations with 32 GB or more are enough for individuals and small teams. Hardware is sized as part of each pilot.

Considering a pilot?

Technical due-diligence pack (under NDA)

Architecture, data flow per mode, record design, component list, test evidence, security questionnaire.

Live verification session (45 min)

We switch modes in front of you, trace an AI edit into the record, and run the verification live.

Community Edition

The free, open-source (AGPL-3.0) Community Edition is a developer workstation with a browser IDE, AI coding agent, semantic search and integrations. It doesn't include the workspaces, automation or audit trail.