Verification

Model-to-code

Check whether generated code implements the actors, actions, states, permissions, and constraints in a Lines Agent Pack.

POST

https://api.nearform.co/v1/adam/evaluations/model-to-code

Request

curl --request POST \
  --url https://api.nearform.co/v1/adam/evaluations/model-to-code \
  --header "Authorization: Bearer ADAM_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "workspace_id": "ws_demo",
  "input": "Replace with the endpoint-specific Lines artifact or research question",
  "human_review_required": true
}'

Request

curl --request POST \
  --url https://api.nearform.co/v1/adam/evaluations/model-to-code \
  --header "Authorization: Bearer ADAM_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "workspace_id": "ws_demo",
  "input": "Replace with the endpoint-specific Lines artifact or research question",
  "human_review_required": true
}'

Request

curl --request POST \
  --url https://api.nearform.co/v1/adam/evaluations/model-to-code \
  --header "Authorization: Bearer ADAM_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "workspace_id": "ws_demo",
  "input": "Replace with the endpoint-specific Lines artifact or research question",
  "human_review_required": true
}'

200

400

{
  "id": "verify_model_to_code_01HXYZ",
  "object": "verify-model-to-code",
  "status": "queued",
  "beta": true,
  "human_review_required": true
}

200

400

{
  "id": "verify_model_to_code_01HXYZ",
  "object": "verify-model-to-code",
  "status": "queued",
  "beta": true,
  "human_review_required": true
}

200

400

{
  "id": "verify_model_to_code_01HXYZ",
  "object": "verify-model-to-code",
  "status": "queued",
  "beta": true,
  "human_review_required": true
}

Beta access: ADAM is currently in beta. Create a Lines account — https://nearform.co/account — and apply for access — https://nearform.co/apply.

What this endpoint does: ADAM converts product meaning into explicit checks and compares them with the submitted code and runnable evidence.

Input: Provide the Agent Pack, repository or patch, test command, and environment constraints.

Output: Returns verified requirements, failures, untested assumptions, and evidence locations. Results distinguish absence from inconclusive inspection.

Human review: A passing report complements code review and testing; it does not replace security, accessibility, or domain review.

Semantic drift

Need help? Contact Support

Join our Discord Community

Questions? Contact Sales

Request

curl --request POST \
  --url https://api.nearform.co/v1/adam/evaluations/model-to-code \
  --header "Authorization: Bearer ADAM_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "workspace_id": "ws_demo",
  "input": "Replace with the endpoint-specific Lines artifact or research question",
  "human_review_required": true
}'

200

400

{
  "id": "verify_model_to_code_01HXYZ",
  "object": "verify-model-to-code",
  "status": "queued",
  "beta": true,
  "human_review_required": true
}