Fast model Provider A
Approved - Support
- Sales
- Ops
Model hub
Every approved model, in one place.
Connect the providers you trust, choose the models your company allows and decide which teams and agents can use each one.
Advanced model Provider B
Approved - Legal
- Finance
Private model Your own key
Approved - HR
- Finance
Choice for teams. Control for admins.
No lock in
Use models from more than one provider, and change your mind later without rebuilding your agents.
Only approved models
Admins decide which models are allowed. Agents cannot reach anything that is not on the list.
Access by team and agent
Give legal a careful model, give support a fast one, and keep sensitive work on a private provider.
One list of approved models
See the models your workspace can use, which provider each one comes from and where it is being used today.
- Models from several providers
- Your own provider keys
- One place to approve or retire a model
Fast model Provider A
Approved - Support
- Sales
- Ops
Advanced model Provider B
Approved - Legal
- Finance
Private model Your own key
Approved - HR
- Finance
Model access by team and agent
Set which teams and agents can use each model. A model that is not approved for a team never shows up in its runs.
Works with auto routing
Auto routing picks from the models in the hub, so every task lands on an approved model that fits its quality bar and cost.
Task Summarize vendor contract
- Fast model Lowest costSlow right now
- Balanced model Meets the quality barRouted here
- Advanced model Higher costNot needed
Fallback is automatic. The run keeps going and the switch is logged.
How it works
From request to recorded result.
-
Connect a provider
Add the providers your company already uses.
-
Approve models
Choose which of their models are allowed.
-
Set access
Decide which teams and agents can use each one.
-
Agents use them
Runs only ever reach approved models.
Every feature runs inside the same six controls.
Identity, access, approvals, supervision, audit and policy apply to every agent and every run, whichever part of the workspace it happens in.
See governance and audit- Identity
- Access
- Approvals
- Supervision
- Audit
- Policy
FAQ
Model hub: questions and answers
Short answers to what teams ask before they put this part of SoftworkerAI to work.
Contact us directlyWhich providers can we use?
You can connect the large language model providers your company already works with and use your own keys. Ask us about the providers on your list.
Can different teams use different models?
Yes. Each model can be limited to specific teams and agents.
What happens when we stop using a model?
Retire it in the hub. Agents move to the other approved models and nothing reaches the retired one.
Do we pay for models through SoftworkerAI?
You can run on your own provider keys, so model usage is billed by your provider and tracked in your workspace.
The multiplayer workspace for humans and AI agents is how teams move beyond prompting and safely hand AI real work. It gives people one place to plan, approve, and oversee execution, so they can run work with AI agents they can govern and trust.