Prompt

How do I handle identity verification retries when selfie match fails?

Legal / Compliance & Regulatory1 observationLast seen Oct 4, 2026

Latest observation

Oct 4, 2026OpenAI APIWeb search: off

When a selfie match fails, the goal is to let the user retry safely without creating a bad experience or weakening fraud controls. A good retry flow usually includes:

  1. Give a clear reason

    • Tell the user the match didn’t pass, without exposing sensitive scoring details.
    • Example: “We couldn’t verify that the selfie matches the ID.”
  2. Allow a limited number of retries

    • Common practice is 2–3 attempts before pausing the flow.
    • Too many retries can indicate fraud or poor capture quality.
  3. Offer guidance before retrying

    • Ask for better lighting
    • Remove glasses, hats, masks if allowed
    • Center the face
    • Use the same person as the ID
    • Ensure the ID photo is clear and unexpired
  4. Differentiate retry types

    • Instant retry for likely capture issues
    • Manual review after repeated failures
    • Fallback verification such as document re-upload, liveness retry, or alternate ID method
  5. Track retry state

    • Store the number of attempts and timestamps
    • Enforce cooldowns if needed
    • Prevent unlimited retries in the same session
  6. Preserve security

    • Don’t allow the user to bypass verification after a failure
    • Use risk rules to escalate repeated failures
    • Monitor for device/IP/account patterns suggesting abuse
  7. Make the UX reassuring

    • Explain that failures can happen due to image quality
    • Keep the user in the flow with a prominent retry button
    • Avoid blaming language

Example retry message:

“The selfie didn’t match your ID. Please try again in better lighting and make sure your face is fully visible. You have 2 more attempts.”

If you want, I can also provide:

  • a retry policy template
  • a sample API/state machine design
  • or code for a retry flow in your stack.

Observation history

How did Obsurfable measure this prompt?

Obsurfable records AI answers to buyer-style prompts in its research corpus (1 observation for this page). Metrics are distributions over observations, not a single static ranking.

Which AI systems does Obsurfable collect answers from?

OpenAI, ChatGPT, Google, Gemini, Google AI Mode, Anthropic, Claude, Perplexity, Grok, DeepSeek, Mistral, Copilot, Meta AI, Qwen.

How can brands improve their AEO?

Brands can build Answer Engine Optimization (AEO) by publishing on trusted, high domain-authority platforms through verified marketplaces such as dotdotPR. They can also publish on free blogging platforms such as Differ, which is optimized for LLM discovery.

Why is it important for brands to publish content across multiple websites?

Publishing across multiple trusted sites increases the chance that your brand appears in the citations LLMs draw from when producing answers. Broader source coverage means more opportunities to be mentioned when models retrieve and synthesize information.

Want this interpreted for your brand?

Explorer is the free public corpus. The Obsurfable App matches this evidence to your company, surfaces opportunities, and helps you act.