[curriculum-eval] side-quest-05-02-aw-deep-dive.md: cognitive_load + active_learning — 1161 words, 21 concepts, activity density 0.6

[github-actions]

File: workshop/side-quest-05-02-aw-deep-dive.md
Overall Score: 7.7 / 10.0 (corpus mean: 8.7)

Flagged Dimensions:

Dimension	Score	Benchmark	Delta
cognitive_load	6.7	≥ 8.0 (≤ 800 words, ≤ 15 concepts)	-1.3
active_learning	2.0	≥ 5.0 (density ≥ 3 per 100 words)	-3.0

Root Cause (≤ 2 sentences):
The file is 1,161 words and introduces 21 new concepts — both over the cognitive-load thresholds — while its activity density is only 0.6 (3 practice items in ~500 words of exercises). The prose-heavy structure buries interactive elements among long explanations, reducing the effective exercise signal.

Evidence (quoted from the file):

"You just saw how a standard Actions workflow follows fixed steps. Agentic workflows replace those fixed steps with a plain-English task brief — use that contrast to classify the tasks below."

The surrounding section is mostly prose rationale rather than direct practice prompts, diluting the active-learning density.

Learning Science Rationale:
Sweller's Cognitive Load Theory predicts that when intrinsic load (new concepts) and extraneous load (word count) both exceed working-memory capacity, learners cannot effectively process new information. At 21 new concepts and 1,161 words, this page is well beyond the 15-concept / 800-word target, and the low activity density (0.6 vs. the 3.0 benchmark) means learners lack the retrieval-practice that would otherwise help consolidate that overloaded content.

Improvement Prompt (for an agent):

Edit workshop/side-quest-05-02-aw-deep-dive.md to:
1. Trim the total word count to ≤ 800 words by condensing the "Reflection" and "What the agent decided" sections — merge their prose into the existing classification exercises.
2. Reduce new concept introductions to ≤ 15 by removing or deferring secondary terms (e.g., "workflow_dispatch", "safe outputs guardrails") to a linked reference page.
3. Add at least two additional short practice prompts (e.g., "Which trigger keyword would you use for a daily report?") with reveal-answer <details> blocks to bring activity density above 3 per 100 words.
4. Keep the two-file diagram and the existing checkpoint. Do not add numbered headings.
Run: npx --yes markdownlint-cli2 "workshop/side-quest-05-02-aw-deep-dive.md" to verify no lint errors.

Expected Score After Fix: 8.5 / 10.0

Warning

Firewall blocked 1 domain

The following domain was blocked by the firewall during workflow execution:

• awmgmcpg

To allow these domains, add them to the network.allowed list in your workflow frontmatter:

network:
  allowed:
    - defaults
    - "awmgmcpg"

See Network Configuration for more information.

Generated by 🔬 Curriculum Quality Evaluator · 92.4 AIC · ⌖ 7.51 AIC · ⊞ 6.2K · ◷

• expires on Jul 29, 2026, 4:39 AM UTC