Drive, Microsoft 365, Slack, CRM and more
Documents, conversations, tools and processes in one layer every agent and every person can ask, with the permissions you already have.
Works with the tools you already have
Documents
Google Drive, SharePoint, OneDrive and Dropbox, read with each file's own permissions.
Email and calendar
Microsoft 365 and Google Workspace: read, draft and file, with approval before anything is sent.
Messaging
Slack and Teams, for copilots your teams talk to and alerts they act on.
CRM and finance
HubSpot, Salesforce, Pennylane and your ERP, read and written both ways.
Your own systems
APIs, databases and internal tools, connected by your engineer.
Permissions respected
An agent sees only what the person behind it is allowed to see.
What your teams see
Answers with sources
Every claim links to the document it came from.
Connected sources
Sync state and permissions for every tool.
Search across tools
One question, every system.
Connected to the tools your teams already use
The foundation reads from them and agents write back, with your permissions.
- Google DriveDocuments
- Microsoft 365Documents
- NotionDocuments
- GmailEmail
- OutlookEmail
- SlackMessaging
- Microsoft TeamsMessaging
- HubSpotCRM
- SalesforceCRM
- ZoomMeetings
- AsanaProjects
- PennylaneFinance
Built for companies that answer to clients
The controls your IT and legal teams ask for, on from the first day.
Made and hosted in Europe
Platform and data stay in the European Union.
Single sign-on
Your identity provider, your rules, one login for every agent.
Roles and approvals
Who can run, edit and approve each agent, per team.
Audit logs
Every run, source and approval recorded and exportable.
GDPR
A data processing agreement and a register of every processor.
EU AI Act
Transparency and human oversight built into every workflow.
Questions teams ask first
Which AI models do you use?
We are model-agnostic. Each agent runs on the model that does its job best, from Anthropic, OpenAI, Google DeepMind, Mistral AI or Meta, and we can change it without rebuilding the agent.
Where is our data hosted?
In the European Union. The platform is built and hosted in Europe, and your data is never used to train a model.
How long until the first agent is live?
Usually four to eight weeks after the audit. The audit itself takes three to four weeks and ends with a roadmap ranked by return on investment.
Do we need a technical team?
No. A forward-deployed engineer does the build inside your tools. Your people review and approve what the agents produce.
See Zastral on your own work
A 30-minute demo on one of your real workflows, and a view of the hours it gives back.