Cohere API and Dome

1. 01

   Add the connections

   The provider id is cohere. Dome uses Cohere's compatibility endpoint, https://api.cohere.ai/compatibility/v1, and Cohere's own model ids.

   $ dome models add command-a-plus-cohere \
     --provider cohere \
     --model command-a-plus-05-2026 \
     --api-key "$COHERE_API_KEY" \
     --attributes '{"approved_for":"legal"}' \
     --gateway prod-gateway
    
   $ dome models add command-a-cohere \
     --provider cohere \
     --model command-a-03-2025 \
     --api-key "$COHERE_API_KEY" \
     --attributes '{"approved_for":"legal"}' \
     --gateway prod-gateway

2. 02

   Pool them

   Command A Plus answers first and Command A second. The pool's name is what agents send.

   $ dome models pool create command-a-plus \
     --failover-max all --gateway prod-gateway
    
   $ dome models pool member add command-a-plus command-a-plus-cohere --priority 0
   $ dome models pool member add command-a-plus command-a-cohere --priority 1

3. 03

   Point your agent at the Gateway

   Change the base URL to the Gateway and the key to the agent's own. OpenAI-compatible SDKs need nothing else.

   from openai import OpenAI
    
   client = OpenAI(base_url=f"{GATEWAY_URL}/v1", api_key=DOME_AGENT_KEY)
   client.chat.completions.create(
       model="command-a-plus",
       messages=[{"role": "user", "content": "List the indemnity clauses in this contract."}],
   )

Commands and rules tested against a Dome workspace on October 1, 2026. For anything about Cohere itself, see Cohere's documentation.

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 approved_for && resource.approved_for == "legal" };