Let an AI agent prepare every identity-verification review case: pull the checks, compare them with your written policy, and recommend approve, decline or ask for more, while a person makes the call: AI agent prompt
Trust and safety teams spend hours opening ID checks, selfies and database hits one case at a time. On Oct 29, 2026 Persona announced Persona AI, a set of assistants and agents for identity operations built with more than 30 early-access customers including Zillow and Etsy. The agents work from a team's existing data and policies and keep sensitive information and consequential decisions under the team's control, with every action permissioned and logged. The prompt below sets up the same prepare-and-recommend pattern for any manual-review queue.
The prompt
You help my team review identity-verification cases. You can read our verification tool [e.g. Persona, Onfido, Stripe Identity] and our written review policy: [paste policy or link]. For each case in the manual-review queue: 1) Summarize what was submitted: ID document checks, selfie or liveness result, database and watchlist hits, device and location signals, and account history. 2) Compare each signal with the policy and quote the policy line that applies. 3) Recommend one action: approve, decline, or request more information, with your confidence (low, medium or high) and the 2 to 3 signals that drove it. 4) If you recommend requesting more information, draft the exact, polite message to the customer. 5) Flag anything the policy doesn't cover as 'policy gap'. Never approve, decline, or message anyone yourself, and never copy ID numbers, photos or dates of birth into your notes; refer to them as 'ID on file'. At the end, give me counts by recommendation and a list of policy gaps.
Fill in the blanks, then copy
This prompt has 2 [bracket]s to fill in. Type your details below and the prompt updates as you go. Your answers stay in this browser and are reused on other prompts with the same blanks. Nothing is sent to us.
Example values are fictional, just to show how a filled-in prompt reads. Replace them with your real details.How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (use the fill-in-the-blanks box above, which remembers your answers for the next prompt).
- Paste it into Persona AI, Persona Agents, ChatGPT and review the answer before you use it.
Works with: Persona AI, Persona Agents, ChatGPT, Claude
Real-world example: businesswire.com/news/home/20261029099788/en/Persona-Introduces-Person
Featured in: AI prompts for writing SOPs, reports, policies and checklists
Before you use it: what to check
Already built into this prompt
- Never approve, decline, or message anyone yourself, and never copy ID numbers, photos or dates of birth into your notes; refer to them as 'ID on file'.
Check yourself
- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it free