# Start a forensics run on a stored file
Source: https://docs.file.ai/api-reference/forensics/start-a-forensics-run-on-a-stored-file

> Queues forensics on a file that is already stored, identified by file_id. Takes a JSON body — unlike extract, split and classify there is no upload.

post /prod/v1/forensics

Queues forensics on a file that is already stored, identified by file_id. Takes a JSON body — unlike extract, split and classify there is no upload.

spec_filter names detectors to run (see the schema for the full list,
e.g. web_presence, ai_gen_detection, layout_parse). Forensics results
land under `forensics.{key}` on GET; layout_parse lands under
mapping.layout_parse (FileElements). web_presence reports whether the
image is present on the web from file metadata (layer1) and a
reverse-image search (layer2); other detectors report FileMap's fields.

Always returns 202 Accepted with a run_id; poll
GET /v1/forensics/runs/{run_id} until status is complete or error. Web
presence can take up to ~180 seconds. A run still queued or running
after ~6 minutes is stuck — retry it via
POST /v1/forensics/runs/{run_id}/retry. DELETE the run once you have
the result; the file itself is not affected.