Verification

Handoff check

Predict agent failure risk and generate testable acceptance criteria before implementation starts.

POST

https://api.nearform.co/v1/adam/evaluations/handoff-readiness

Request

curl --request POST \
  --url https://api.nearform.co/v1/adam/evaluations/handoff-readiness \
  --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/handoff-readiness \
  --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/handoff-readiness \
  --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": "evaluate_handoff_readiness_01HXYZ",
  "object": "evaluate-handoff-readiness",
  "status": "queued",
  "beta": true,
  "human_review_required": true
}

200

400

{
  "id": "evaluate_handoff_readiness_01HXYZ",
  "object": "evaluate-handoff-readiness",
  "status": "queued",
  "beta": true,
  "human_review_required": true
}

200

400

{
  "id": "evaluate_handoff_readiness_01HXYZ",
  "object": "evaluate-handoff-readiness",
  "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 estimates whether a coding agent is likely to fail because the handoff is underspecified, inconsistent, or missing observable success conditions.

Input: Provide the intended coding task, Agent Pack, target stack, and implementation constraints.

Output: Returns failure-risk factors, missing assumptions, generated acceptance criteria, and a recommended handoff decision.

Human review: People decide whether to proceed, revise the model, narrow the task, or add a live checkpoint.

State coverage

Need help? Contact Support

Join our Discord Community

Questions? Contact Sales

Request

curl --request POST \
  --url https://api.nearform.co/v1/adam/evaluations/handoff-readiness \
  --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": "evaluate_handoff_readiness_01HXYZ",
  "object": "evaluate-handoff-readiness",
  "status": "queued",
  "beta": true,
  "human_review_required": true
}