Skip to main content
POST
/
alignment
/
agent
/
{agent_id}
/
simulate
Simulate gateway evaluation against the alignment card
curl --request POST \
  --url https://api.mnemom.ai/v1/alignment/agent/{agent_id}/simulate \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "candidate_input": {
    "messages": [
      {}
    ]
  },
  "candidate_tool_call": {
    "tool_name": "<string>",
    "tool_args": {}
  }
}
'
{
  "ok": true,
  "conditions": [
    "<string>"
  ],
  "suggestions": [
    "<string>"
  ],
  "gateway_decision": {
    "violations": [
      {}
    ],
    "warnings": [
      {}
    ],
    "missing_receipts": [
      "<string>"
    ]
  },
  "observer_assessment": {
    "violations": [
      {}
    ],
    "warnings": [
      {}
    ]
  },
  "evaluated_at": "2023-11-07T05:31:56Z"
}

Authorizations

Authorization
string
header
required

Supabase JWT token in Authorization: Bearer header

Path Parameters

agent_id
string
required

Agent identifier (e.g. smolt-abc123)

Body

application/json
candidate_input
object

Hypothetical conversation snippet.

candidate_tool_call
object

Hypothetical tool invocation. Synthesized into an assistant message with a toolUses block when candidate_input.messages is absent.

Response

Simulation result.

ok
boolean
required
resource
enum<string>
required
Available options:
alignment
allowed
enum<string>
required
Available options:
true,
false,
conditional
conditions
string[]
required
suggestions
string[]
required
gateway_decision
object
required
observer_assessment
object
required
evaluated_at
string<date-time>
required