The right modelfor each agent.
Anthropic, OpenAI, Google and xAI models, chosen per agent. Your permissions, approvals and record stay the same whichever model does the work.
One platform,many models.
Chosen per agent
Each agent is set to the model that suits its job.
The major providers
Anthropic, OpenAI, Google and xAI models.
One gateway
PRESHos reaches every model through one gateway, under the same permissions and the same record.
See what each runtook.
Every run is kept with its model, its steps, its tokens and its cost.
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.
Tied to one model today?
Tell us which AI tools your team uses. We will talk through how agents on PRESHos would use the model that fits each job.