At a Glance

  • Provider: Walsh University
  • Credential: Applied AI: Prompting, Testing, and Verification Certificate
  • Length: 8 contact hours (8 clock hours) in four 2-hour live virtual sessions with the instructor
  • Format: Live virtual, instructor led. Every session combines short technical explanations, demonstrations, individual practice, and hands-on work by participants.
  • Prerequisites: None. No programming is required.
  • Tools: An approved AI assistant such as Microsoft Copilot (or related company-specific platform) and a spreadsheet. Participants need a computer with a current browser and an account for the AI assistant, set up before the first session. The skills carry over to other AI tools.
  • Data: Participants use an approved AI tool and only information authorized for that environment. The instructor provides practice documents and data when workplace information cannot be used.

This course teaches professionals to configure, test, and use generative AI tools for technical work. Participants build structured prompts that control the format and quality of AI output, run the same task with and without source material to see how AI behaves, test AI capability against known answers, and apply AI to technical documentation, spreadsheet formulas, data cleanup, and structured records. Every output is verified against its source before it is used.

Learning Outcomes

By the end of this course, participants will be able to:

  • Configure an approved AI assistant, including its settings and saved instructions, and apply safeguards for confidential, regulated, and sensitive information..
  • Identify unsupported or inaccurate AI output by checking it against source material.
  • Build prompts that specify an objective, context, source material, constraints, and a required output format, and iterate and version them against a checklist.
  • Create a reusable prompt template with variables and a fixed output schema, test it on multiple inputs, and measure consistency across repeated runs.
  • Map a work task to an AI capability, such as summarizing, extracting, classifying, or transforming, and test its accuracy on sample data against an answer key.
  • Evaluate a proposed AI use for data readiness, technical feasibility, risk, and expected impact.
  • Use AI to draft and revise technical documentation and procedures, generate and test spreadsheet formulas, clean and standardize data, and turn notes or logs into structured records.
  • Verify each AI output and record the corrections made.

Training Outline

Each 2-hour session is built from short technical explanations, instructor demonstrations, and hands-on work that participants complete during the session.

1. Practical AI Foundations and Safe Configuration (2 hours): 

  • Technical objectives: identify what generative AI can and cannot do and why outputs can be inaccurate or unsupported; configure an approved AI assistant, including settings and saved instructions; apply safeguards for confidential, regulated, and sensitive information; identify when human review is required.
  • Hands-on work in the session: the instructor demonstrates the same task run with and without source material, then participants run it themselves, find and log unsupported statements, configure their assistant, and sort sample inputs into those that are authorized for use and those that are not.
  • Tools: Microsoft Copilot (or related company-specific platform).
  • Deliverable: a Personal AI Use and Guardrail Card listing suitable tasks, tasks requiring caution, information that requires authorization, and situations requiring human review.

2. Structured Prompts and Output Control (2 hours):

  • Technical objectives: build a prompt from an objective, context, role, source material, constraints, and a required output format; require structured output such as a table, fixed fields, or a template; instruct the tool to flag missing information instead of guessing; iterate and version prompts and compare results against a checklist.
  • Hands-on work in the session: the instructor improves a weak prompt step by step, then participants do the same with their own weak prompt, record each version and its result, convert the final prompt into a reusable template with variables, define pass or fail criteria for the output schema, test it on 5 inputs, and repeat each run 3 times to measure consistency.
  • Tools: Microsoft Copilot (or related company-specific platform) and a spreadsheet.
  • Deliverable: a Reusable Prompt Template and test log.

3. Capability Mapping and Use-Case Testing (2 hours):

  • Technical objectives: map a work task to an AI capability such as summarizing, extracting, classifying, or transforming; identify the input data a task requires and whether it is ready; test a use case on sample data and measure accuracy against an answer key; rate technical feasibility, risk, and expected impact.
  • Hands-on work in the session: the instructor tests one use case live and scores it, then participants select three work tasks, run each on provided sample data, calculate an accuracy percentage for each against an answer key, and record data readiness, feasibility, risk, and expected impact for each.
  • Tools: Microsoft Copilot (or related company-specific platform) and a spreadsheet.
  • Deliverable: a Capability Test Record for three use cases.

4. Applying AI Tools to Technical Content and Workflow Tasks (2 hours):

  • Technical objectives: draft and revise technical documentation and procedures; generate, explain, and test spreadsheet formulas; clean and standardize a data list; turn notes or logs into a structured table; verify every output and record corrections.
  • Hands-on work in the session: the instructor demonstrates one task from each type, then participants apply their Session 2 prompt template to four tasks using provided material: convert rough notes into a step-by-step procedure, build a spreadsheet formula and test it against 5 known cases, clean and standardize a messy data list and check row counts and field formats, and summarize a log into a structured table, verifying each output and recording corrections.
  • Tools: Microsoft Copilot (or related company-specific platform) and a spreadsheet.
  • Deliverable: an AI Task Playbook of verified prompts, example outputs, and notes on the review each requires.

Assessment and Credentials

Each session ends with a deliverable that the instructor reviews. Walsh University awards the Applied AI: Prompting, Testing, and Verification Certificate for attending all four sessions and completing the deliverables.

Skills That Transfer Beyond

The skills taught in this course are not specific to any one employer. They are transferable across industries, because every organization that adopts generative AI needs people who can control its output, verify it against sources, protect sensitive information, and test whether it works for a given task. The course teaches these methods with a widely used AI assistant and practice material, not any organization's systems, and its safeguards align with the NIST AI Risk Management Framework, a national standard used across sectors.

Data and Privacy in Class

Participants use an approved AI tool and only information authorized for that environment. The instructor provides practice documents and data when workplace information cannot be used.