Home labs & practical projects
Compare AI task types using a fictional service desk
A project to do with your own tools, with guidance on what to create and capture.
For existing holders and historical learning. Check the current credential before starting exam preparation.
What you could create
A team revisits historical AI fundamentals learning and wants to distinguish classification, extraction and generation in a service-desk workflow.
| Evidence | What to capture |
|---|---|
| AI task-to-workflow map | Show the inputs, scope and decisions behind this record. Different task types use suitable evaluation criteria. |
| Evaluation and responsible-use worksheet | Include the evidence supporting your conclusion. The proposal includes a non-AI baseline for comparison. |
What you'll need
Document, spreadsheet or diagram tool
Create six fictional tickets with categories, short text and selected structured fields. Use this as a concepts exercise; consult current offerings before choosing a platform.
Project record
Keep the working files for ai task-to-workflow map and record assumptions as you go.
Current reference material
Use the linked provider resources to verify the features, access terms and version relevant to your project.
Access & cost
No paid platform is needed for the written version. Use a document, spreadsheet or diagram tool you already have.
The organisation and records are fictional. Write down assumptions; do not substitute confidential employer information.
Suggested milestones
- 1
Plan and investigate
Map each proposed feature to an AI task and a business need.
- 2
Develop your approach
Identify the input data, expected output and a simple evaluation method.
- 3
Verify and explain
Explain errors, bias and human review requirements for each task.
Useful resources
Use these resources to deepen your understanding and check key details.
A useful starting point
Create six fictional tickets with categories, short text and selected structured fields. Use this as a concepts exercise; consult current offerings before choosing a platform.
What a good result looks like
- Different task types use suitable evaluation criteria.
- The proposal includes a non-AI baseline for comparison.
Finish the project
Keep the decision record and note unanswered questions. A written design is not evidence that a technical control has been tested.
Independent home-project guidance, not an official vendor lab or a claim of complete exam coverage. Use your own tools and label the work accurately.