2. Click on the three dots next to your assistant's name.# 3. Click on Red Team# 4. The AI Red Teaming Attack page will open.# 5. Click on Get Started# 6. Type a Name for the attack that reflects the scenario or risk area you want to test.# 7. In the red teaming tab, choose the Attack Type you want to run# 8. Click on Next# 9. From the list of available Probes, select the probe set that matches your chosen attack type or scenario.# Each probe, converter, and detector will include a description outlining its use case to help you select the appropriate option for your scenario. For a complete guide on the different types of probes, converters, and detectors, view Assistant Red Teaming 10. Click on Next# 12. Click on Next# 13. Choose the Scorer that will evaluate the assistant’s responses.# 14. Click on Start Attack# 15. A new job will appear in the jobs table with status Pending. After a short time, the status will update to Running as the attack is executed.# 16. Click on View Attack Details to review your configuration: Attack Type, Probe, Converter, and Scorer to ensure they match your testing goals.# 17. A modal will open where you can view the complete details of your attack.# 18. If your attack is in Running state and you want to stop it, click on Cancel Attack .# 19. Click on Cancel Attack . Remember that this action can't be undone.# 20. Once the attack completes, the job status will change to Completed .# 21. Click on View Result# 22. Here you can inspect the prompts, model responses, and Scorer outputs for each red team example.#
