Features
The platform sits between your data and the AI models and records everything that happens along the way.
A sovereign execution and governance layer
Three functions that happen on every task an agent runs.
Agents connected to the organization's documents, databases and internal systems.
Access, cost and sensitivity policies decide whether each task runs on a local, private or authorized model.
Every run stores the source consulted, the user, the model, the cost and the result.
Automatic routing across the leading models
Sensitivity policies decide what runs on a local model and what may go to an authorized provider. Data that must stay within national infrastructure is processed on your own infrastructure.
The set of available models depends on the plan you are on. See which models each plan includes
Per-run auditing
Corporate logs record user activity. Deep Agents records every run: the sources consulted, the model used, the cost and the result produced.
- Time of the run
- What was executed
- User and responsible department
- Model used, local or from a provider
- Cost of the run
- Export of the record as CSV
Your data, in your territory
Agents work directly on the organization's databases, documents and internal systems. Nothing is copied into third-party tools.
Sensitivity analysis decides what may be processed outside national infrastructure. Everything else stays in your environment, with the source of each answer on record.
You decide where the data lives
Deploy on-premises, in a VPC or in the cloud your organization already uses. Access follows the permissions and policies your team defines.
Your own hardware, air-gapped if needed.
Isolated perimeter in the cloud you contract.
AWS, Azure, GCP or a national provider.
How agents reach people
A published agent can be opened on a page of its own, embedded in the organization's website or consumed directly through the API.