# Working Well with AI: Prompting, Verifying, and Learning from Real Cases

**Course FAST-16** · 6 hours · Instructor: Wadood Chaudhary · Presented by 7formations

## Session 1. Asking well: prompting basics (2 hours)

- What a prompt is; weak versus strong prompts
- The four elements: context, instruction, structure, audience
- Four techniques: step-by-step, iterative, role, constraint
- Common prompting mistakes and when to start fresh
- **Lab 1: Prompt makeover (W1 prompt makeover log).**

## Session 2. Checking well: evaluating and verifying AI output (2 hours)

- Why AI output needs evaluation
- Five types of output error
- The five-step evaluation
- Verification techniques, lateral reading, and invented citations
- Checking data insights and written content
- **Lab 2: Error hunt and evaluation record (W2).**

## Session 3. Learning from cases and building a safe workflow (2 hours)

- Five workplace cases and two public incidents
- Success factors and common challenges
- The five-step responsible-use workflow
- Documenting AI use and monitoring over time
- **Lab 3: Case analysis and safe AI workflow card (W3, W4 final).**

## Worksheets and deliverables

- W1 Prompt makeover log
- W2 Evaluation record (five steps, error types, verification used)
- W3 Case analysis
- W4 Safe AI workflow card (final)
- W5 Ask-check-own pocket card (take-home)

## Attendance and completion

- Attendance is recorded at the start and end of every session (live virtual: platform attendance log plus an instructor roll call or poll; in-person: signed sheet).
- A trainee must attend 100% of instructional hours. A missed session may be made up by attending the same session in another scheduled cohort within 30 days; the make-up is logged the same way.
- A trainee must submit every required lab deliverable and score 'Meets' on the final applied task.
- Each completion record is tied to the trainee, the employer FEIN, and the course number, and is kept for the contract retention period.
- Incomplete trainees are not reported as completions and are not billed to anyone. FAST AI pays for completions only; employers and trainees are never charged.
- Optional asynchronous pre-work (under 10% of course time) is supplemental, is not counted as instructional hours, and never substitutes for a live session.

## Assessment rubric

Each criterion is scored Not yet / Meets / Strong. Completion requires Meets on every criterion for the final deliverable (resubmission allowed within the course window).

| Criterion | Meets standard |
| --- | --- |
| Prompting | Four elements present; answer improved with two follow-ups |
| Error spotting | 4 of 5 seeded error types found and named |
| Verification | Three techniques used; every cited source checked |
| Case reasoning | Benefits, challenges, lessons, and a safeguard stated |
| Safe workflow | Five steps written for a real task; AI-use note included |