AI Verification Basics – Checking Answers Before You Trust Them
Lesson 1: Command Thinking for Free AI Foundations
Lesson Objectives
By the end of this lesson, students should be able to:
- Explain what a command is in this provider context.
- Distinguish real commands from natural-language requests and UI buttons.
- Write a command request with role, source, desired output, constraints, and acceptance checks.
Lesson Content
Verification starts by identifying claims, dates, numbers, legal/medical/financial advice, and anything that affects a real decision. Students should ask the AI to mark uncertainty and then verify against primary or authoritative sources.
Professional Use Case: A learner checks an AI-generated course-pricing answer before using it in a business plan.
Student task: Perform the following use scenario. Copy the first AI answer into a text editor or notes document. Then write one clarification prompt, which is a short follow-up that tells the AI exactly what to fix, add, remove, or explain.
Starter scenario: Ask the AI to list all factual claims in an answer and rank which need verification.
Troubleshooting: If the command is unavailable, check whether it depends on a workspace, paid plan, enabled tool, file type, browser/app context, or region. If the output is shallow, add source material, examples, exclusion rules, and a definition of done. If the output contains claims, verify against an authoritative source before using it.
Quality Rubric:
- The command includes enough context to prevent generic output.
- The result is tied to a real deliverable.
- The student records at least one verification step.
- Sensitive data is removed or minimized.
Enroll to continue this lesson.
The preview above shows the lesson objectives and opening lesson content. Enroll to view the full lesson, complete the practice work, and take the lesson quiz.
