File: workshop/05-agentic-workflows-intro.md
Overall Score: 5.43 / 10.0 (corpus mean: 6.14)
Flagged Dimensions:
| Dimension |
Score |
Benchmark |
Delta |
| active_learning |
2.4 |
density ≥ 3 → 10 |
-7.6 |
| cognitive_load |
~6.7 (word component only; 1,107 words vs ≤800 ideal) |
≤ 800 words |
-3.3 |
Root Cause (≤ 2 sentences):
At 1,107 words this is one of the five longest files in the corpus, and although it contains three good activities (label the two-file structure, agentic-vs-standard classification, write-a-task-brief), the activity density is only 0.72 because the ratio of explanatory prose (three key terms table, two-file structure section, multiple diagram callouts) to actual code-blocks/checklist-items is skewed toward reading over doing. missing_checkpoint is a false positive from the shortcode regex bug — a real 6-item checkpoint exists at line 120.
Evidence (quoted from the file):
"An Agentic Workflow is a plain-English task brief that an AI agent executes inside GitHub Actions... Think of it like a scheduled digest: every morning it reads your inbox and sends you a summary — no keyboard required." followed by three separate diagram/picture blocks and a two-file-structure table before the first activity appears.
Learning Science Rationale:
Mayer's multimedia principle holds that pairing explanatory diagrams with concise text (rather than diagrams plus extended prose) improves learning, but here three separate <picture> diagrams are each preceded or followed by a full paragraph of restated explanation, adding redundant verbal channel load per Mayer's redundancy principle without a proportional increase in the learner's own active practice (only 3 short free-response activities across 1,107 words).
Improvement Prompt (for an agent):
Edit workshop/05-agentic-workflows-intro.md to raise activity density and trim length toward the ~800-word target. Specifically:
1. For each of the three <picture> diagrams (three-terms, two-file-structure, actions-vs-agentic), trim the surrounding prose paragraph to one sentence that directly primes what to look for in the diagram, removing restated explanation that duplicates the diagram's own content (Mayer's redundancy principle).
2. Move the "Three key terms" table content into the diagram caption or a single sentence instead of a standalone table plus a diagram covering the same three terms.
3. Add one additional short hands-on checkpoint immediately after "Activity 1 — identify the parts" (e.g. ask the learner to paste the on: value they found) to raise activity_density before Activity 2.
4. Keep all three existing activities and the final checkpoint; do not remove content, only tighten the connective prose.
Re-run the corpus scoring script and confirm word_count moves toward 800-900 and activity_density rises above 1.0.
Expected Score After Fix: 6.5 / 10.0
Generated by 🔬 Curriculum Quality Evaluator · copilot · auto · 76.7 AIC · ⌖ 17.4 AIC · ⊞ 9.5K · ◷
File:
workshop/05-agentic-workflows-intro.mdOverall Score:
5.43 / 10.0(corpus mean:6.14)Flagged Dimensions:
Root Cause (≤ 2 sentences):
At 1,107 words this is one of the five longest files in the corpus, and although it contains three good activities (label the two-file structure, agentic-vs-standard classification, write-a-task-brief), the activity density is only 0.72 because the ratio of explanatory prose (three key terms table, two-file structure section, multiple diagram callouts) to actual code-blocks/checklist-items is skewed toward reading over doing.
missing_checkpointis a false positive from the shortcode regex bug — a real 6-item checkpoint exists at line 120.Evidence (quoted from the file):
Learning Science Rationale:
Mayer's multimedia principle holds that pairing explanatory diagrams with concise text (rather than diagrams plus extended prose) improves learning, but here three separate
<picture>diagrams are each preceded or followed by a full paragraph of restated explanation, adding redundant verbal channel load per Mayer's redundancy principle without a proportional increase in the learner's own active practice (only 3 short free-response activities across 1,107 words).Improvement Prompt (for an agent):
Expected Score After Fix:
6.5 / 10.0