Idéal pour
- Partir d'un prompt structuré et réutilisable plutôt que d'une conversation vierge.
- Adapter le prompt à vos propres données tout en conservant l'intention d'origine.
- Les workflows liés à Business & Pro.
Analyste professionnel des risques de profil OSINT (par ex. pour Linkedin)
Remplir ce promptAnalyse les profils LinkedIn pour identifier les incohérences, les possibles embellissements du CV et les signaux d’alerte liés à l’authenticité, dans une approche OSINT structurée.
Modèle de prompt
Act like a due-diligence investigator and OSINT analyst specialized in identifying suspicious or inauthentic professional profiles. Maintain a {{Tone:[tones]}} tone while avoiding defamation and sticking strictly to the evidence provided.
Your goal is to examine the following profile data: {{Profile Data: The Linkedin profile is attached, Paste the scraped LinkedIn profile text here}}
Determine whether there are dubious signs, inconsistencies, or patterns commonly associated with impersonation, résumé inflation, fake credentials, or coordinated scam/fraud behavior—without making definitive accusations. Apply an analysis strictness level of {{Strictness: *High, Medium, Low}}.
Task: Analyze the profile text and produce an “Authenticity & Risk Review”.
Step-by-step process:
1) Parse the profile into: identity basics, headline/about, experience, education, certifications, skills, recommendations, activity/posts, and contact/links.
2) List potential red flags as bullet points. For each red flag, include:
- What you observed (quote the exact snippet),
- Why it may be concerning (the pattern it matches),
- At least one benign explanation (how it could be legitimate),
- What evidence would confirm/refute it (specific checks).
3) Check internal consistency: dates, overlaps, seniority vs. tenure, role scope vs. company size, geographic logic, language/grammar patterns, repeated buzzwords, overly broad claims, unverifiable awards, and mismatched education timelines.
4) Provide a risk rating (Low / Medium / High) and a 0–100 risk score. Explain the score in 3–6 bullets tied to evidence.
5) Give a verification checklist prioritized by impact (top 10 actions), including: items to Google, documents to request, questions to ask in a call, and what to look for on company sites or registries.
6) End with a short, cautious summary: “What looks solid” vs “What needs verification”.
Output format:
- Snapshot
- Red flags (with evidence + benign explanations + verification)
- Consistency checks
- Risk score + rationale
- Verification checklist
- Summary
Guide du prompt
Comment l'utiliser
- Copiez le modèle de prompt complet.
- Remplacez chaque variable par votre propre contexte ou choisissez l'une des options suggérées.
- Collez le prompt complété dans ChatGPT, Claude, Gemini ou un autre assistant IA.
Variables de ce prompt
Tone
Liste prédéfinie
[tones]
Profile Data
The Linkedin profile is attached, Paste the scraped LinkedIn profile text here
Strictness
High, Medium, Low
Exemple de départ
Act like a due-diligence investigator and OSINT analyst specialized in identifying suspicious or inauthentic professional profiles. Maintain a [tones] tone while avoiding defamation and sticking strictly to the evidence provided. Your goal is to examine the following profile data: The Linkedin profile is attached Determine whether there are dubious signs, inconsistencies, or patterns commonly associated with impersonation, résumé inflation, fake credentials, or coordinated scam/fraud behavior—without making definitive accusations. Apply an analysis strictness level of High. Task: Analyze the profile text and produce an “Authenticity & Risk Review”. Step-by-step process: 1) Parse the profile into: identity basics, headline/about, experience, education, certifications, skills, recommendations, activity/posts, and contact/links. 2) List potential red flags as bullet points. For each...
Comment fonctionnent les variables
Syntaxe des variables
Les variables sont entourées de {{ et }} et suivent ce modèle :
{{variable name: option1, option2, option3 }}
Variables prédéfinies
Une sélection peut référencer une liste de variables prédéfinie à l'aide de crochets. Elles apparaissent en [orange] et fournissent des valeurs courantes comme des couleurs, des tons ou des langues.
{{Tone: [tones] }}
Listes de choix personnalisées
Vous pouvez aussi fournir une liste de choix en ligne, séparés par des virgules.
{{Format: bullet points, paragraphs, numbered list }}
Astuce : vous n'avez pas besoin de l'application PUCO pour utiliser ces prompts ! Copiez simplement le modèle et remplacez chaque section {{…}} par votre propre texte directement dans ChatGPT, Claude, Gemini ou tout autre assistant IA.