Skip to content
SupaCloud Docs
Select themeSelect language

`POST /api/intelligence/agent-experiments` — create an experiment. Admin-only.

POST
/api/intelligence/agent-experiments
curl --request POST \
  --url https://example.com/api/intelligence/agent-experiments \
  --header 'Content-Type: application/json' \
  --data '{ "dataset": "example", "evaluators": "example", "name": "example", "project_id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0", "purpose": "example", "status": "example", "stop_criteria": "example", "variants": [ { "budget_policy": "example", "config": "example", "endpoint": "example", "harness": "example", "is_control": true, "model": "example", "name": "example", "prompt_policy": "example", "provider": "example", "runner": "example", "tool_profile": "example" } ] }'

Request Bodyrequired

Section titled “Request Bodyrequired”
Media typeapplication/json
object
dataset
evaluators
name
required
string
project_id
string | null format: uuid
purpose
string | null
status
string | null
stop_criteria
variants
required
Array<object>
object
budget_policy
config
endpoint
string | null
harness
string | null
is_control
boolean | null
model
required
string
name
required
string
prompt_policy
provider
required
string
runner
required
string
tool_profile
string | null
Examplegenerated
{
  "dataset": "example",
  "evaluators": "example",
  "name": "example",
  "project_id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0",
  "purpose": "example",
  "status": "example",
  "stop_criteria": "example",
  "variants": [
    {
      "budget_policy": "example",
      "config": "example",
      "endpoint": "example",
      "harness": "example",
      "is_control": true,
      "model": "example",
      "name": "example",
      "prompt_policy": "example",
      "provider": "example",
      "runner": "example",
      "tool_profile": "example"
    }
  ]
}

Responses

Section titled “Responses”

200

Section titled “200”
Media typeapplication/json
object
experiment
required
object
completed_at
string | null format: date-time
created_at
required
string format: date-time
created_by
string | null format: uuid
dataset
required
evaluators
required
id
required
string format: uuid
name
required
string
project_id
string | null format: uuid
purpose
required
string
recommendation
string | null
recommendation_confidence
number | null format: double
status
required
string
stop_criteria
required
updated_at
required
string format: date-time
workspace_id
required
string format: uuid
harness_comparison
required
Array<object>
object
accepted_runs
required
integer
cost_per_accepted_patch
number | null format: double
cost_usd
required
number format: double
cost_waste_usd
required
number format: double
harness
string | null
key
required
string
label
required
string
minutes_per_accepted_patch
number | null format: double
model
string | null
provider
string | null
regression_rate
required
number format: double
retry_rate
required
number format: double
review_acceptance_rate
number | null format: double
runner
string | null
sample_size
required
integer
scope_violation_rate
required
number format: double
score
required
number format: double
success_rate
required
number format: double
test_pass_rate
number | null format: double
timeout_rate
required
number format: double
tokens_per_accepted_patch
number | null format: double
tool_error_rate
required
number format: double
leaderboard
required
Array<object>
object
accepted_runs
required
integer
cost_per_accepted_patch
number | null format: double
cost_usd
required
number format: double
cost_waste_usd
required
number format: double
harness
string | null
key
required
string
label
required
string
minutes_per_accepted_patch
number | null format: double
model
string | null
provider
string | null
regression_rate
required
number format: double
retry_rate
required
number format: double
review_acceptance_rate
number | null format: double
runner
string | null
sample_size
required
integer
scope_violation_rate
required
number format: double
score
required
number format: double
success_rate
required
number format: double
test_pass_rate
number | null format: double
timeout_rate
required
number format: double
tokens_per_accepted_patch
number | null format: double
tool_error_rate
required
number format: double
model_comparison
required
Array<object>
object
accepted_runs
required
integer
cost_per_accepted_patch
number | null format: double
cost_usd
required
number format: double
cost_waste_usd
required
number format: double
harness
string | null
key
required
string
label
required
string
minutes_per_accepted_patch
number | null format: double
model
string | null
provider
string | null
regression_rate
required
number format: double
retry_rate
required
number format: double
review_acceptance_rate
number | null format: double
runner
string | null
sample_size
required
integer
scope_violation_rate
required
number format: double
score
required
number format: double
success_rate
required
number format: double
test_pass_rate
number | null format: double
timeout_rate
required
number format: double
tokens_per_accepted_patch
number | null format: double
tool_error_rate
required
number format: double
recommendations
required
Array<object>
object
basis
required
string
confidence
required
number format: double
recommendation
required
string
sample_size
required
integer
scope
required
string
runs
required
Array<object>
object
accepted
required
boolean
active_ms
integer | null format: int64
artifacts
required
bridge_events
required
cache_read_tokens
integer | null format: int64
cache_write_tokens
integer | null format: int64
cost_usd
number | null format: double
created_at
required
string format: date-time
dataset_case_id
string | null
experiment_id
required
string format: uuid
finished_at
string | null format: date-time
human_rating
number | null format: double
id
required
string format: uuid
input_tokens
integer | null format: int64
lint_passed
boolean | null
output_tokens
integer | null format: int64
reasoning_tokens
integer | null format: int64
regression
required
boolean
result
required
retry_count
required
integer format: int32
review_accepted
boolean | null
run_id
string | null format: uuid
scope_violation
required
boolean
started_at
string | null format: date-time
status
required
string
task_class
required
string
task_id
string | null format: uuid
task_label
required
string
tests_passed
boolean | null
timeout
required
boolean
tool_error_count
required
integer format: int32
turns
integer | null format: int32
variant_id
required
string format: uuid
wall_ms
integer | null format: int64
workspace_id
required
string format: uuid
task_class_matrix
required
Array<object>
object
task_class
required
string
variants
required
Array<object>
object
accepted_runs
required
integer
cost_per_accepted_patch
number | null format: double
cost_usd
required
number format: double
cost_waste_usd
required
number format: double
harness
string | null
key
required
string
label
required
string
minutes_per_accepted_patch
number | null format: double
model
string | null
provider
string | null
regression_rate
required
number format: double
retry_rate
required
number format: double
review_acceptance_rate
number | null format: double
runner
string | null
sample_size
required
integer
scope_violation_rate
required
number format: double
score
required
number format: double
success_rate
required
number format: double
test_pass_rate
number | null format: double
timeout_rate
required
number format: double
tokens_per_accepted_patch
number | null format: double
tool_error_rate
required
number format: double
winner_key
string | null
winner_label
string | null
variants
required
Array<object>
object
budget_policy
required
config
required
created_at
required
string format: date-time
endpoint
string | null
experiment_id
required
string format: uuid
harness
required
string
id
required
string format: uuid
is_control
required
boolean
model
required
string
name
required
string
prompt_policy
required
provider
required
string
runner
required
string
tool_profile
required
string
workspace_id
required
string format: uuid
Examplegenerated
{
  "experiment": {
    "completed_at": "2026-04-15T12:00:00Z",
    "created_at": "2026-04-15T12:00:00Z",
    "created_by": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0",
    "dataset": "example",
    "evaluators": "example",
    "id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0",
    "name": "example",
    "project_id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0",
    "purpose": "example",
    "recommendation": "example",
    "recommendation_confidence": 1,
    "status": "example",
    "stop_criteria": "example",
    "updated_at": "2026-04-15T12:00:00Z",
    "workspace_id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0"
  },
  "harness_comparison": [
    {
      "accepted_runs": 1,
      "cost_per_accepted_patch": 1,
      "cost_usd": 1,
      "cost_waste_usd": 1,
      "harness": "example",
      "key": "example",
      "label": "example",
      "minutes_per_accepted_patch": 1,
      "model": "example",
      "provider": "example",
      "regression_rate": 1,
      "retry_rate": 1,
      "review_acceptance_rate": 1,
      "runner": "example",
      "sample_size": 1,
      "scope_violation_rate": 1,
      "score": 1,
      "success_rate": 1,
      "test_pass_rate": 1,
      "timeout_rate": 1,
      "tokens_per_accepted_patch": 1,
      "tool_error_rate": 1
    }
  ],
  "leaderboard": [
    {
      "accepted_runs": 1,
      "cost_per_accepted_patch": 1,
      "cost_usd": 1,
      "cost_waste_usd": 1,
      "harness": "example",
      "key": "example",
      "label": "example",
      "minutes_per_accepted_patch": 1,
      "model": "example",
      "provider": "example",
      "regression_rate": 1,
      "retry_rate": 1,
      "review_acceptance_rate": 1,
      "runner": "example",
      "sample_size": 1,
      "scope_violation_rate": 1,
      "score": 1,
      "success_rate": 1,
      "test_pass_rate": 1,
      "timeout_rate": 1,
      "tokens_per_accepted_patch": 1,
      "tool_error_rate": 1
    }
  ],
  "model_comparison": [
    {
      "accepted_runs": 1,
      "cost_per_accepted_patch": 1,
      "cost_usd": 1,
      "cost_waste_usd": 1,
      "harness": "example",
      "key": "example",
      "label": "example",
      "minutes_per_accepted_patch": 1,
      "model": "example",
      "provider": "example",
      "regression_rate": 1,
      "retry_rate": 1,
      "review_acceptance_rate": 1,
      "runner": "example",
      "sample_size": 1,
      "scope_violation_rate": 1,
      "score": 1,
      "success_rate": 1,
      "test_pass_rate": 1,
      "timeout_rate": 1,
      "tokens_per_accepted_patch": 1,
      "tool_error_rate": 1
    }
  ],
  "recommendations": [
    {
      "basis": "example",
      "confidence": 1,
      "recommendation": "example",
      "sample_size": 1,
      "scope": "example"
    }
  ],
  "runs": [
    {
      "accepted": true,
      "active_ms": 1,
      "artifacts": "example",
      "bridge_events": "example",
      "cache_read_tokens": 1,
      "cache_write_tokens": 1,
      "cost_usd": 1,
      "created_at": "2026-04-15T12:00:00Z",
      "dataset_case_id": "example",
      "experiment_id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0",
      "finished_at": "2026-04-15T12:00:00Z",
      "human_rating": 1,
      "id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0",
      "input_tokens": 1,
      "lint_passed": true,
      "output_tokens": 1,
      "reasoning_tokens": 1,
      "regression": true,
      "result": "example",
      "retry_count": 1,
      "review_accepted": true,
      "run_id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0",
      "scope_violation": true,
      "started_at": "2026-04-15T12:00:00Z",
      "status": "example",
      "task_class": "example",
      "task_id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0",
      "task_label": "example",
      "tests_passed": true,
      "timeout": true,
      "tool_error_count": 1,
      "turns": 1,
      "variant_id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0",
      "wall_ms": 1,
      "workspace_id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0"
    }
  ],
  "task_class_matrix": [
    {
      "task_class": "example",
      "variants": [
        {
          "accepted_runs": 1,
          "cost_per_accepted_patch": 1,
          "cost_usd": 1,
          "cost_waste_usd": 1,
          "harness": "example",
          "key": "example",
          "label": "example",
          "minutes_per_accepted_patch": 1,
          "model": "example",
          "provider": "example",
          "regression_rate": 1,
          "retry_rate": 1,
          "review_acceptance_rate": 1,
          "runner": "example",
          "sample_size": 1,
          "scope_violation_rate": 1,
          "score": 1,
          "success_rate": 1,
          "test_pass_rate": 1,
          "timeout_rate": 1,
          "tokens_per_accepted_patch": 1,
          "tool_error_rate": 1
        }
      ],
      "winner_key": "example",
      "winner_label": "example"
    }
  ],
  "variants": [
    {
      "budget_policy": "example",
      "config": "example",
      "created_at": "2026-04-15T12:00:00Z",
      "endpoint": "example",
      "experiment_id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0",
      "harness": "example",
      "id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0",
      "is_control": true,
      "model": "example",
      "name": "example",
      "prompt_policy": "example",
      "provider": "example",
      "runner": "example",
      "tool_profile": "example",
      "workspace_id": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0"
    }
  ]
}