Extraction & Benchmarks

Screenshot model

Reconstruct likely actions, fields, states, permissions, and workflows from an existing app screenshot.

POST

https://api.nearform.co/v1/adam/extract/screenshot

Request

curl --request POST \
  --url https://api.nearform.co/v1/adam/extract/screenshot \
  --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/extract/screenshot \
  --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/extract/screenshot \
  --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": "extract_model_from_screenshot_01HXYZ",
  "object": "extract-model-from-screenshot",
  "status": "queued",
  "beta": true,
  "human_review_required": true
}

200

400

{
  "id": "extract_model_from_screenshot_01HXYZ",
  "object": "extract-model-from-screenshot",
  "status": "queued",
  "beta": true,
  "human_review_required": true
}

200

400

{
  "id": "extract_model_from_screenshot_01HXYZ",
  "object": "extract-model-from-screenshot",
  "status": "queued",
  "beta": true,
  "human_review_required": true
}

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

What this endpoint does: ADAM uses high-resolution GUI analysis to propose a Lines model behind a visual interface. The output distinguishes visible evidence from inferred product behavior.

Input: Provide an image reference, optional crop regions, product context, and any known user role.

Output: Returns visual objects, proposed Nodes, candidate bindings, ambiguity flags, and follow-up questions.

Human review: Professional UIs contain small targets and dense controls. Review grounding and crop choices before trusting extracted meaning.

Need help? Contact Support

Questions? Contact Sales

Request

curl --request POST \
  --url https://api.nearform.co/v1/adam/extract/screenshot \
  --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": "extract_model_from_screenshot_01HXYZ",
  "object": "extract-model-from-screenshot",
  "status": "queued",
  "beta": true,
  "human_review_required": true
}

ยฉ 2026

Nearform Physical AI Inc. ยท All rights reserved