Building with AI — Assessment

A Assessment Summary

This document maps Building with AI to the AESOP assessment blueprint, scoring each covered skill on a 0–4 scale and documenting the Bloom's Taxonomy ceiling, assessment methods used, and standards alignment.

11

Skills Assessed

of 28 total blueprint skills

8

Skills at Apply / Analyze

high-ceiling coverage

Create

Bloom's Ceiling

M8 capstone — Ship Something Real

4

Assessment Methods

quiz · module-test · lab · project

6

Standards Covered

AI4K12, EU AI Act, NIST, O*NET, ISTE, WEF

4

Primary Domain Skills

Prompt Engineering — all score 3–4

B Bloom's Taxonomy Coverage

Distribution across the course. Heavy Apply/Analyze weighting reflects this course's builder orientation. Create appears in M8 where students ship a complete, novel AI-powered workflow.

2%

12%

Apply 45%

Analyze 30%

9%

2%

Remember 2%

Understand 12%

Apply 45%

Analyze 30%

Evaluate 9%

Create 2%

C Skills Coverage by Domain

Scores use the 0–4 blueprint scale: 0 = not addressed, 1 = mentioned only, 2 = explained with examples, 3 = applied to scenarios, 4 = synthesized / evaluated / created.

Prompt Engineering PRIMARY

Skill	Score	Ceiling	Assessment Methods	Coverage
Write Clear Prompts write-clear-prompts	4	Evaluate	Quiz Module Test Lab Project	M1 M4 M5 M6 M8 — core focus
Design Multi-Turn Conversations design-multi-turn-conversations	4	Evaluate	Quiz Module Test Lab Project	M2 M5 M6 M8 — multi-turn workflows built
Leverage System Prompts leverage-system-prompts	4	Evaluate	Quiz Module Test Lab Project	M1 M4 M5 M6 — design + evaluation
Optimize Output Formats optimize-output-formats	3	Analyze	Quiz Module Test Lab	M4 patterns, M5/M6 structured outputs

AI Fundamentals Partial

Skill	Score	Ceiling	Assessment Methods	Coverage
Grasp LLM Behavior grasp-llm-behavior	3	Analyze	Module Test Lab	M2 context/memory, M3 debate
Recognize AI Limitations recognize-ai-limitations	2	Apply	Module Test Lab	M3 M7 — when AI shouldn't be used

Generative AI Partial

Skill	Score	Ceiling	Assessment Methods	Coverage
Use Generative AI Tools use-generative-ai-tools	3	Apply	Module Test Lab Project	M5 M6 M8 — builds with live AI APIs

AI Applications Partial

Skill	Score	Ceiling	Assessment Methods	Coverage
Identify AI Use Cases identify-ai-use-cases	3	Analyze	Module Test Lab	M3 M7 debates — AI appropriateness
Evaluate AI Solutions evaluate-ai-solutions	2	Evaluate	Module Test Lab	M7 human handoff, M8 reflection

AI Systems & Agents Partial

Skill	Score	Ceiling	Assessment Methods	Coverage
Implement AI Workflows implement-ai-workflows	3	Analyze	Module Test Lab Project	M5 M6 M8 — working artifacts produced

AI Ethics & Governance Partial

Skill	Score	Ceiling	Assessment Methods	Coverage
Understand AI Ethics understand-ai-ethics	2	Analyze	Module Test Lab	M3 M7 debates — ethical lens, not primary

D Assessment Method Breakdown

Lesson Quizzes

Remember · Understand · Apply

M1 — prompt quality identification
M2 — context window mechanics
M4 — pattern recognition & selection
Multiple-choice + true/false, 3–4 items per lesson

Module Test (exam.html)

Understand · Apply · Analyze

30 standards-mapped questions
Mixed format: MC, short-answer, scenario analysis
Covers all 8 module skill areas
Scored 0–100, maps to proficiency bands

Conversational Labs

Apply · Analyze · Evaluate

SKILL labs (M1 M2 M4) — ~25 min each
BUILD labs (M5 M6 M8) — ~30 min each
DEBATE labs (M3 M7) — ~20 min each
AI tutor feedback, rubric-based 0–4 scoring

Capstone Project

Analyze · Evaluate · Create

M8 "Ship Something Real" — portfolio artifact
Complete AI-powered workflow with documentation
Human-in-the-loop checkpoint analysis required
Rubric-scored: design, implementation, reflection

E Standards Alignment

Standard	Relevant Items / Articles	Modules
AI4K12	Big Idea 1 — Perception · Big Idea 2 — Representation & Reasoning · Big Idea 4 — Natural Interaction	M1 M2 M3 M4 M5 M6 M7 M8
EU AI Act	Article 4 — AI Literacy · Article 14 — Human Oversight · Article 22	M3 M7 M8
NIST AI RMF	Map function · Measure function	M5 M6 M8
O*NET	Technology Skills — AI/ML tools · Programming	M1 M4 M5 M6 M8
ISTE	Designer 4c · Computational Thinker 5c	M4 M5 M6 M8
WEF	AI and Big Data skills cluster	M1 M2 M4 M5 M6 M8

F Gaps & Recommendations

Skills Not Covered by This Course

RAG / vector databases
Fine-tuning
Agent orchestration
AI security
Data analytics
Governance frameworks

Building with AI is intentionally scoped to using and building with AI tools — prompt engineering, workflow construction, and human-in-the-loop design. It does not cover infrastructure concerns (RAG, vector databases, fine-tuning), agent orchestration architectures, or AI security hardening.

Ethics coverage is present through the M3 and M7 debate modules but remains instrumental (when is AI appropriate?) rather than comprehensive governance treatment. Pair this course with AI Ethics & Decision Making for full governance coverage including policy analysis, bias auditing, and accountability frameworks.

G Portfolio Artifact

Capstone — M8 Build Lab

Ship Something Real

A complete AI-powered workflow documented with design decisions, prompt architecture, and human-in-the-loop checkpoints. Students define a real problem, build a working solution using the prompt patterns and conversation structures developed across the course, and produce a written artifact explaining what they built, why they made the choices they did, and where a human must stay in the loop.

EU AI Act — Art. 4 NIST AI RMF — Map O*NET Technology Skills AI4K12 Big Idea 4 ISTE Designer 4c