Skip to content
NTPU AI Learn

AI 102 Apply

Design the context for a real task with a Context Canvas

What the Context Canvas is for

The Context Canvas is the capstone of AI 102. For one real AI task you decide what the AI must know, where it comes from, which source is authoritative, how fresh it must be, how sensitive it is, and whether to include, retrieve, remember or exclude it.

What you fill in

  • Goal and instructions
  • A table of information: why needed, source, Source of Truth, version or date, update frequency
  • Sensitivity (Public, Internal, Confidential, Restricted) and strategy (Include, Retrieve, Remember, Exclude) with a reason for each
  • Verification and a failure plan for missing, stale, conflicting and unavailable information
  • Which results need human review

Warning

Restricted information must be excluded. The form rejects a Restricted item that is not marked Exclude.

Example

A procurement evaluation report: requirements and quotes are included, policy and history are retrieved, the manager's format is remembered, and the credit card number is excluded. See the example on the canvas page.

Before you submit

Warning

Do not enter secrets, credentials, personal data, client data or sensitive information you are not authorized to share. Use illustrative or public examples only.

What comes next: AI 201

Some context cannot be provided in advance, or it keeps changing. How can an AI obtain it safely? That is the question of AI 201: MCP, tools and trusted data. As always, a human stays responsible for reviewing the result.

Go to the canvas

What you need to complete

  • Complete all six AI 102 modules
  • Score at least 80% on the course post-test
  • To earn the Context Engineering Capability Certificate, also submit a Context Canvas and have it reviewed and passed by a Credential Admin against the rubric

How you are assessed

A Credential Admin scores the Context Canvas against six weighted domains: Task & Goal Framing, Information Relevance & Authority, Freshness & Sensitivity Handling, Strategy Assignment, Verification & Failure Handling, and Human Review. A score of at least 15 out of 18, with no critical-fail rule triggered, is a PASS; 12 or below, or any triggered critical-fail rule, is a FAIL.

Info

This scoring logic is published so you know what is being assessed. It is not the same as revealing quiz answers.

Practical evidence

  • A recorded rubric result (PASS, REVISION_REQUIRED, or FAIL) with no critical-fail rule triggered
  • A PASS records capability evidence separately for each of the six fine-grained AI 102 competencies (Prompt vs. Context Diagnosis, Context Taxonomy, Context Quality Assessment, Context Strategy Selection, Context Failure Diagnosis, Context Canvas Design)

What you can earn

AI 102 Course Completion Certificate: earned once you complete all six modules and meet the post-test threshold, with no Context Canvas submission required. Context Engineering Capability Certificate: requires a separately submitted and reviewed Context Canvas. The two are independent and do not affect each other.

What this credential does not mean

This credential confirms the holder completed AI 102's required course and post-test, or (for the certificate) demonstrated task framing, information judgment, strategy selection, and verification on the Context Canvas.

  • It does not mean the holder holds a formal data-security or governance professional license or is qualified for a specific role
  • It does not mean any specific context the holder designs later is automatically correct or safe
  • It does not mean human review can be skipped before a high-impact decision (Human, AI, Human)

What next?