check
This tool on every surface: CLI · MCP · Python · JavaScript · Go · Java · .NET
Check a claim about a recorded session: a model with a fresh context — none of yours — reads the recording (each call, its result or error, and the screen and screenshot after it) through read-only tools, and answers passed, failed or inconclusive with the observations it rests on. These call app_check.
check
public Map<String, Object> check(String claim, String record)
public Map<String, Object> check(String claim, String record, String model)
Asks an independent model whether a claim holds in a recording. The
model reads only the recording, in a fresh context, and answers with
status (passed, failed or inconclusive), summary and
evidence. A model's judgment is not proof. This asks Claude
through the Anthropic API, which needs a credential, is a paid call, and
is not yet measured; check(String, String, String) names another.
@param claim what should be true, precisely @param record the .zip a trace saved @return the verdict
Asks a named model whether a claim holds in a recording, as
check(String, String) does.
@param claim what should be true, precisely
@param record the .zip a trace saved
@param model "openai:<name>" for one served through the
OpenAI-compatible API (Ollama where mobium runs, unless
MOBIUM_AI_BASE_URL names another server); null for Claude
@return the verdict
Examples
Ask a model on this machine whether a claim holds in a recording
Map<String, Object> v = device.check("After card 3 was tapped, it was shown face up as the Blue Morpho.", "card.zip", "openai:qwen2.5:14b");
System.out.println(v.get("status") + " " + v.get("summary"));