Image detector for travel scam evidence review
Triage photos submitted as scam evidence—street signs, tickets, receipts, storefronts, or screenshots—before citing them in guides or social posts.
Business value
- Protects trust in travel-scam evidence image workflows before automated agents take irreversible action.
- Creates a concrete QA policy agents can apply consistently.
- Turns risk evidence into review, revision, or provenance requests.
Agent job to be done
Act as the travel-scam evidence image trust triage layer. Score or prepare the asset, inspect evidence, and choose allow, revise, human_review, or reject based on workflow stakes.
format: articleintended_use: citedomain: travel scam visual evidence
When to call VeracityAPI
Run after asset intake/export and before publish, moderation, citation, training, payment, or account-impacting decisions.
What image URL to submit
Public HTTPS image URL for the exact asset the agent will publish, moderate, cite, or use as evidence.
Decision policy
- allow: low risk and low-stakes use with no conflicting local signals.
- revise: medium risk or evidence that can be fixed by replacement, disclosure, or better provenance.
- human_review: high risk, sensitive claims, identity/fraud implications, or evidentiary use.
- reject: repeated high-risk assets combined with policy violations or missing provenance.
Request template
curl https://api.veracityapi.com/v1/analyze -H "Authorization: Bearer DOC_KEY" -H "Content-Type: application/json" -d '{"type":"text","content":"Paste content here","context":{"format":"article","intended_use":"publish"}}'Automation recipe
- Agent receives final image URL and local workflow metadata.
- Agent calls POST /v1/analyze with type=image.
- Store score, recommended_action, and evidence categories in the workflow record.
- Allow low-risk assets; queue medium/high-risk assets for review or replacement.
- Rescore replacement images before publication or use.
Evidence spans agents should inspect
- synthetic-looking texture or cadence
- geometry, text, label, transcript, or continuity mismatch
- weak or missing provenance
- signals that conflict with local metadata
Policy pseudocode
if (result.recommended_action === "allow") continueWorkflow(); if (result.recommended_action === "revise") rewriteWith(result.evidence, result.recommended_fixes); if (result.recommended_action === "human_review") queueForHumanReview(result); if (result.recommended_action === "reject") discardOrRebuild();
KPIs to track
- assets triaged
- human-review precision
- bad publishes or decisions prevented
- false-positive appeal rate
- average review latency
What can go wrong
- Not proof that an image is AI-generated; use evidence with provenance/source checks.
- Do not use a single score as forensic evidence.
- Combine VeracityAPI with local metadata, source reputation, and human escalation.
Cost and latency notes
Image analysis is a flat $0.02 per image. The endpoint accepts HTTPS image URLs, stores no image bytes, and logs only a URL hash plus hostname. Current v0.1 latency is vision-model-bound, so preflight balance and retry carefully.
Agent evaluation checklist
- Does this workflow have a costly failure mode from manipulated or synthetic-looking visuals?
- Can the agent store evidence categories without storing raw image bytes or full URLs?
- Should this workflow fail open, fail closed, or queue human review if image scoring is unavailable?
- Which field drives policy: recommended_action, risk_level, content_trust_score, or synthetic_image_risk?
- What local provenance check should complement the API score?