
Agents do the work. Your people stay in charge.
Who can do what and who signed off, how each request is checked, what every run cost, and how PRESHos connects to the systems you already run.
Who can do what,and who signed off.
Permissions
Roles for people and for agents. An agent never has more access than its owner.
Approvals
The agent proposes, the owner decides. Reviews land in one inbox.
Audit
A record of who did it, which agent, which tools and what changed.

Identity, policy and evidenceacross agent execution.
Enterprise identity

SSO and IdP integration
- MFA support, directory sync
- Active membership, session
Authorization
Tenant and membership bindingRBAC and tool policyUser contextRoles, ownership
Agent identityAssigned roles
Object, field and record scopes

- Allow
- Approval
- Deny
Runtime choice

- Cloud
- Isolated session
- microVMs
- Local
- Enrolled Mac
- User workspace
Connected systems

Configurable cloud egress
- SSRF safeguards
- Scoped access
- MCP, APIs and AI models
Shared security services

Protected data
- Encrypted storage
- Private file access
- Point-in-time recovery

Secrets vault
- Google Cloud Secret Manager
- Scoped runtime grants
- Server-side credentials

Audit and approvals
- Run and tool event traces
- Human approval records
- Actor, action, outcome
Usage, results and costfor every run.

Cost per task
Every run carries its steps, tokens and cost.
By work item
Rolled up by person, agent and the work it was for.
Nothing hidden
Costs are marked actual or estimated, never left blank.
Connectors, pluginsand automations.
Connectors
Records sync with the systems you run, mapped field by field.
Plugins
Bundles of skills and tools, installed once and granted to agents.
Automations
A trigger starts an agent or an action.


Relatedreading.
More on Platform
AI & Automation
AI Works on a Copy: Approval Before Anything Reaches a Live System
Agents can do real work on a working copy of your data while a person approves what goes back. Here is how a digital twin and an approval gate work together.

AI Engineering
Choosing a Model per Agent: Match the Model to the Job
Different agent jobs suit different AI models. Here is how to choose a model per agent, compare options fairly and keep your controls the same throughout.

AI Engineering
Field-Level Permissions for Agents: Control Down to the Field
Field-level permissions decide which parts of a record an agent can read or change. Here is how roles, scopes and fields combine, with a worked example.

See it on your own workflow.
Bring us the work you want agents to do. We will walk through the permissions, approvals and connections it needs.