medtests.net · Ask AI

Use MedTests with your AI assistant

ChatGPT, Claude, and other AI assistants can help you find a suitable self-screening. Some assistants can call MedTests tools directly. Others can send you to the relevant test in your browser.

How it works

  1. Briefly describe what is concerning you and how long it has been happening.
  2. Ask the assistant to search the MedTests catalogue for a suitable screening.
  3. Ask why the test fits and what its limits are.
  4. Answer in the chat or open the linked test in your browser.
  5. Consent to scoring after you have checked all your answers.

The result is a screening indication. It does not replace a medical, psychotherapeutic, or diagnostic evaluation.

Three prompts to copy

Example 1

I have been worrying a lot for two weeks and find it hard to switch off. Help me find a suitable self-screening on MedTests. Do not diagnose me.

Example 2

Guide me through the GAD-7 using MedTests. Keep every question and answer option exact, and ask for my explicit consent before scoring.

Example 3

Explain my MedTests result in plain language. Treat it as a screening indication, not a diagnosis, and suggest one appropriate next step.

For AI agents

  1. Identify the person's concern without inferring a diagnosis.
  2. Before asking sensitive questions, explain that the AI provider may process the chat under its own privacy terms.
  3. Retrieve the MedTests catalogue and compare suitable screenings.
  4. Choose a suitable test with documented validation for its exact version and language. If that evidence is missing, explain the limitation and offer the browser self-check without presenting it as validated.
  5. Retrieve the exact questions, answer options, and instructions from MedTests without changing them.
  6. Do not guess or fill in missing answers.
  7. Ask for explicit consent before scoring and let MedTests calculate the result.
  8. Explain the result as a screening indication, not a diagnosis.
  9. Follow safety guidance throughout the flow. Show returned crisis alerts even when the total score is low. If there may be immediate danger, stop the screening, call get_crisis_resources, and provide emergency contacts appropriate to the person's country.

Your information and chat history

Your AI provider may process or retain chat history under its own privacy terms. The MedTests API is stateless and does not store your answers. If you prefer not to put sensitive details in a third-party chat, open the recommended test directly on MedTests and complete it in your browser.

Technical details are available in MedTests for AI agents.