Skip to content
UltimateTeam.ai Docs

Get full decision provenance

GET
/api/v1/decisions/{decision_id}
curl --request GET \
  --url https://api.ultimateteam.ai/api/v1/decisions/example \
  --header 'X-API-Key: <X-API-Key>'

Returns the complete provenance trail for a single decision, including full reasoning chain, all data sources consulted, and expected vs actual outcomes.

Authorizations

Section titled “Authorizations”

Parameters

Section titled “ Parameters ”

Path Parameters

Section titled “Path Parameters”
decision_id
required
Decision Id

The decision UUID to retrieve

string

The decision UUID to retrieve

Responses

Section titled “ Responses ”

200

Section titled “200”

Successful Response

Media typeapplication/json
DecisionDetailResponse

Full provenance response for a single decision.

Attributes: id: Decision UUID. tenant_id: Owning tenant. agent_role: The agent that made the decision. action_type: Category of action. autonomy_level: Autonomy level used. description: Human-readable description. reasoning_chain: Full reasoning trace. confidence_score: Agent confidence (0.0-1.0). data_sources: All data sources consulted. expected_outcome: What the agent predicted. actual_outcome: What actually happened. outcome_quality: Match score between prediction and reality. outcome_measured_at: When outcome was measured. status: Decision status. reversible: Whether decision can be undone. reversed: Whether decision was undone. created_at: When recorded. decided_at: When executed.

object
action_type
required
Action Type
string
actual_outcome
required
Any of:
object
key
additional properties
any
agent_role
required
Agent Role
string
approval_token
Any of:
string
autonomy_level
required
Autonomy Level
integer
calibration_evidence
Any of:
object
key
additional properties
any
confidence_score
required
Any of:
number
created_at
required
Created At
string format: date-time
data_sources
required
Data Sources
Array<object>
object
key
additional properties
any
decided_at
required
Any of:
string format: date-time
description
required
Description
string
execution_plan
Any of:
ExecutionPlan

Structured pre-act plan generated before Level 2+ agent actions.

object
authority
Any of:
object
key
additional properties
any
debate
Any of:
DebateRecord
object
arguments
Arguments
Array<object>
DebateArgument
object
agent_role
required
Agent Role
string
argument
required
Argument
string
stance
required
Stance
string
task_id
required
Task Id
string
decision_id
required
Decision Id
string
error
Any of:
string
net_recommendation
Net Recommendation
string
default: escalate
Allowed values: proceed reconsider escalate
owner_kind
Owner Kind
string
default: decision
Allowed values: decision intention
status
Status
string
default: pending
Allowed values: pending complete blocked
synthesis
Synthesis
string
""
task_ids
Task Ids
object
key
additional properties
string
tenant_id
required
Tenant Id
string
triggered_by
required
Triggered By
string
overall_risk
required
Overall Risk
string
Allowed values: low medium high critical
preference_evidence
Preference Evidence
Array<object>
PreferenceEvidence
object
context_text
required
Context Text
string
id
required
Id
string
outcome
required
Outcome
string
Allowed values: approved rejected
similarity
required
Similarity
number
steps
required
Steps
Array<object>
ExecutionPlanStep

A single step in a pre-act execution plan.

object
action_type
required
Action Type
string
credit_cost
Credit Cost
integer
0
description
required
Description
string
reversible
required
Reversible
boolean
risk_level
Risk Level
string
default: low
Allowed values: low medium high critical
step_number
required
Step Number
integer
task_type
required
Task Type
string
total_credits
required
Total Credits
integer
total_steps
required
Total Steps
integer
expected_outcome
required
Any of:
object
key
additional properties
any
id
required
Id
string
moa_consensus
Any of:
object
key
additional properties
any
outcome_measured_at
required
Any of:
string format: date-time
outcome_quality
required
Any of:
number
reasoning_chain
required
Any of:
string
reversed
required
Reversed
boolean
reversible
required
Reversible
boolean
signal_classifications
Any of:
object
key
additional properties
any
status
required
Status
string
tenant_id
required
Tenant Id
string
Example
{
  "execution_plan": {
    "debate": {
      "net_recommendation": "proceed",
      "owner_kind": "decision",
      "status": "pending",
      "synthesis": ""
    },
    "overall_risk": "low",
    "preference_evidence": [
      {
        "outcome": "approved"
      }
    ],
    "steps": [
      {
        "credit_cost": 0,
        "risk_level": "low"
      }
    ]
  }
}

422

Section titled “422”

Validation Error

Media typeapplication/json
HTTPValidationError
object
detail
Detail
Array<object>
ValidationError
object
ctx
Context
object
input
Input
loc
required
Location
Array
msg
required
Message
string
type
required
Error Type
string
Examplegenerated
{
  "detail": [
    {
      "ctx": {},
      "input": "example",
      "loc": [
        "example"
      ],
      "msg": "example",
      "type": "example"
    }
  ]
}