OpenAI Org approved
Connected Primary Bring your own LLM
Your models. Your keys. Our governance.
Run agents on the provider your company already trusts, and apply the same rules to every model call.
Keep the choices you have already made.
Your provider contract
Use the provider and terms your company has already approved.
Your own keys
Run on your own API keys, so usage is billed by your provider.
Free to change
Add or swap providers later without rebuilding your agents.
Connect your provider
Add your provider and keys once. Agents in your workspace then run on the models you have approved.
Fast model Provider A
Approved - Support
- Sales
- Ops
Advanced model Provider B
Approved - Legal
- Finance
Private model Your own key
Approved - HR
- Finance
Model policies per team and workflow
Decide which model each team and workflow may use, so sensitive work stays on the provider you trust most.
Low risk draft Fast model
Legal reasoning Approved advanced model
Sensitive data Private provider
Central policy
Controls cost, quality, latency, privacy, and task complexity.
Clear cost tracking
See model cost by team, workstream and agent, even when it is billed by your own provider.
184 Runs
37m Turnaround
92% Approval clarity
$428 Model cost
How it works
From request to recorded result.
-
Add your provider
Connect the provider your company uses.
-
Set model policies
Choose models per team and workflow.
-
Agents run on your keys
Usage is billed by your provider.
-
Track the cost
See spend by team, workstream and agent.
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
Bring your own LLM: questions and answers
Short answers to what teams ask before they put this part of SoftworkerAI to work.
Contact us directlyDo we have to use your models?
No. You bring your own provider and keys, and agents run on the models you approve.
Can we use more than one provider?
Yes. Connect several providers and set which models each team and workflow can use.
Who pays for model usage?
When you run on your own keys, usage is billed by your provider. SoftworkerAI tracks it so you can see cost by team and agent.
Can we switch providers later?
Yes. Agents and skills are not tied to one model, so you can change providers without rebuilding them.
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.