GPT and Dome
Run GPT-6 from OpenAI and Azure under one name. Serve GPT from OpenAI directly and from your Azure OpenAI deployment behind one pool. Agents ask for gpt-6-sol, and the Broker tries Azure when OpenAI fails. Rules send legal work to the zero-retention deployment.
Dome provides model brokeringand routing for GPT.
OpenAI first, Azure next
Pool the OpenAI connection and your Azure deployment under gpt-6-sol. When OpenAI fails, the call goes to Azure.
Sensitive work on the right deployment
Tag the Azure connection with its retention terms. A rule keeps legal work off any connection without them.
Spend by agent
Cap each agent's monthly provider spend. The sales assistant can't eat the support team's budget.
GPT with failoverin five steps.
Connect OpenAI and Azure, pool the connections in priority order, and point your agents at the Gateway, with provider keys kept in Dome.
Connect OpenAI
The key goes into Dome's vault and is sent as a bearer token at call time, so agents never hold it.
shelldome models add gpt-openai \ --provider openai \ --model gpt-6-sol \ --api-key "$OPENAI_API_KEY" \ --gateway prod-gatewayConnect Azure OpenAI
Azure needs your resource endpoint, the deployment name and an API version. The key is sent as the api-key header.
shelldome models add gpt-azure \ --provider azure_openai \ --model gpt-6-sol \ --provider-config '{"endpoint":"https://contoso-eu.openai.azure.com","deployment":"gpt-6-sol","api_version":"2024-10-21"}' \ --api-key "$AZURE_OPENAI_API_KEY" \ --attributes '{"retention":"zero"}' \ --gateway prod-gatewayPool them for failover
Members are tried in priority order. Name the pool for the model and agents need no other change.
shelldome models pool create gpt-6-sol \ --failover-max all --gateway prod-gateway dome models pool member add gpt-6-sol gpt-openai --priority 0dome models pool member add gpt-6-sol gpt-azure --priority 1Point your agent at the Gateway
The OpenAI SDK takes the Gateway URL as its base. The agent's Dome key replaces the provider key.
pythonfrom openai import OpenAI client = OpenAI(base_url=f"{GATEWAY_URL}/v1", api_key=DOME_AGENT_KEY)client.chat.completions.create( model="gpt-6-sol", messages=[{"role": "user", "content": "Summarize this call transcript."}],)Cap spend per agent
An agent quota counts every model call that agent makes, through any pool.
shelldome quotas set --subject agent --agent sales-assistant \ --dimension llm --unit provider_usd --limit 200 --window monthly
Legal work stays onzero-retention connections.
When the person an agent acts for is in legal, only connections tagged retention: zero are allowed. Everyone else can use either provider.
cedar
forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)when { principal has act_as && principal.act_as.groups.contains("legal")}unless { resource has retention && resource.retention == "zero" };One call,two outcomes.
Switch the caller or the argument and watch the same call decide differently, with every decision landing in audit.
Connection
agent contract-reviewer · acting as e.walsh
llm:invoke(model: "gpt-azure")
- Agentcontract-reviewer is registered and active
- Callere.walsh verified, groups: legal
- RuleConnection is tagged retention: zero
DecisionAllowed
Bringing it alltogether.
Connecting GPT to registered agents, tools, and identity in Dome completes a governed agent application.
Acting for
Control point
GatewayEvery call decided and audited
RulesGuardsQuotas
Models
Common questionsabout GPT.
More of whatDome works with.
Provider
Anthropic
The Claude API behind the Model Broker: the key held in Dome, every call authorized, metered and audited.
MCP server
GitHub
The GitHub MCP server behind the Tool Gateway, with rules that decide each call on its owner and repository.
Identity
Okta
Okta tokens verified on every agent call, so rules and audit name the person each agent acted for.
Runtime
LangGraph
LangGraph agents with their model calls on the Model Broker and their MCP tools on the Tool Gateway.
Client
Claude Code
Claude Code on a Dome Gateway with per-developer sign-in, rules on every tool call, and audit by name.
Agent service
TinyFish
TinyFish's web agents behind the Tool Gateway, with rules that decide each run on the site it targets.
Talk with ourFDE team.
Or start free, and register your first agent in minutes. Connect it through a gateway, give it rules, and see every call it makes in one audit trail.
Talk with our FDE team
Our engineers design, build and run governed agents for the part of your business you want to change. You see what they deliver.
AI models for enterprise agents: failover, rules and quotas
Every model your agents call goes through the Model Broker. Pool providers for failover, decide who may call each model, and cap what it costs.