A7 AI7 UAE API available

ADVERSE MEDIA / GLOBAL

Multilingual media
screening.

Screen an individual or business across current and archived global news plus open-web indexes, with evidence links, entity-match scoring, risk categories, legal stage, documented coverage, and focused regional packs.

POST/service/adverse_media

AUTHENTICATION

Use your existing AI7 credential

Send your personal AI7 API key as a Bearer token. The media-source credential, query strategy, and private configuration remain server-side.

Authorization: Bearer YOUR_AI7_API_KEY

REQUEST

Screen a person or business

entity_typeenum · required

individual or business.

namestring · required

Primary individual or business name.

aliasesstring[] · optional

Alternate spellings, former names, or transliterations.

countriesstring[] · optional

Up to 20 ISO two-letter country codes used for identity context and focused regional coverage.

languagesstring[] · optional

Up to five languages. Defaults to English and Arabic. Chinese and Russian also activate their matching country pack.

date_from / date_todate · optional

Inclusive publication-date search window.

risk_thresholdnumber · optional

Scores at or above this 0–1 value require review. Default: 0.65.

max_resultsinteger · optional

One to 50 results. Default: 25.


          


          

            
RESPONSE

            
Evidence and explainable scores

            
Every result includes its original URL and separate entity-match, adverse-relevance, source-reliability, severity, and combined risk scores.

            

              
FieldTypeDescription

              
screening_idUUIDUnique screening reference.

              
summary.risk_levelstringHigh, medium, low, or no material results.

              
summary.categoriesobjectCount of results by adverse-event category.

              
statusstringcompleted only when every configured search and AI review stage succeeds; otherwise partial.

              
summary.threshold_statusstringReview required, within threshold, or incomplete coverage.

              
summary.decision_eligiblebooleanFalse whenever the run is partial and must not be treated as a completed compliance decision.

              
coverageobjectCompleteness, per-index attempt counts, languages, dates, and explicit limitations.

              
usageobjectPaid-query usage, cache state, and cost guardrail.

              
results[].titlestringArticle or page title.

              
results[].urlURIOriginal evidence URL.

              
results[].source_typestringNews index, open web, global archive, or official regulatory evidence.

              
results[].excerptstringRelevant indexed excerpt.

              
results[].categoriesstring[]Detected risk categories.

              
results[].legal_stagestringMedia mention, allegation, investigation, charge, arrest, conviction, or regulatory action.

              
results[].entity_match_scorenumberHow strongly the article matches the requested entity.

              
results[].risk_scorenumberCombined, explainable prioritisation score.

              
results[].review_requiredbooleanTrue when the result meets the threshold and has not been excluded by high-confidence AI evidence review.

              
results[].final_dispositionstringReview required, below threshold, or retained for audit but excluded by AI evidence review.

              
results[].ai_classificationobjectOptional bounded AI review containing only entity match, adverse status, categories, legal stage, confidence, and a concise evidence summary.

            

            
Status codes

            

              
200Screening returned; inspect status and summary.decision_eligible before use

              
400Invalid request fields

              
401Missing or invalid AI7 API key

              
502Media indexes temporarily unavailable

            

          


          

            
METHODOLOGY

            
Designed for review, not automated guilt decisions

            
The engine normalizes names and aliases, searches current and archived indexes with controlled retries, removes duplicate URLs, requires an entity-name match, classifies adverse-event terms, and ranks evidence. Regional selections add native-language and country-focused official-source searches inside the fixed 12-query guardrail; eligible Russia business searches also check a free structured regulatory source. High-confidence AI mismatch or non-adverse findings remain in the response for audit but cannot trigger review. Any exhausted source or AI failure makes the run partial, blocks decision eligibility, and requires manual review. A media result is a review lead—not proof of wrongdoing. Qualified human review remains required before taking action.

          


          

            
LIVE TESTER

            
Run an adverse media check

            
The cost guardrail limits each uncached screening to 12 paid search requests plus one bounded AI classification batch. Repeating the same request within 15 minutes uses the cached evidence.

            

              
              

                Regional coverage Select one or more presets
                

                  
                  
                  
                  
                  
                  
                

                
Presets add the mapped country codes and search languages. You can still edit both fields manually.

              

              

                
                
                
                
                
                
                
                
              

              

                Search languages Select up to five
                

                  
                  
                  
                  
                  
                  
                  
                  
                  
                  
                  
                  
                

              

              
              
            

            
API RESPONSEReady

            

            
{
  "message": "Your JSON response will appear here."
}