Skip to content

[curriculum-eval] 05-agentic-workflows-intro.md: active_learning — reveal-style activities under-count toward activity density #3489

Description

@github-actions

File: workshop/05-agentic-workflows-intro.md
Overall Score: 5.43 / 10.0 (corpus mean: 6.14)

Flagged Dimensions:

Dimension Score Benchmark Delta
cognitive_load 8.5 ≤ 800 words -0.8 (1,107 words, over by ~300)
active_learning 2.4 activity density ≥ 3 (0.72 measured) -7.6

Root Cause (≤ 2 sentences):
Despite having three labeled "Activity" sections (identify the parts, agentic-or-standard, write a task brief), the page only contains 2 code blocks and 6 checklist items against 1,107 words, so measured activity density (0.72) is far below the 3.0 benchmark — the "activities" are mostly read-and-reveal <details> prompts rather than code blocks or checklist-verifiable actions the rubric counts. The word count also exceeds the 800-word ideal by roughly 300 words, compounding the cognitive-load penalty.

Evidence (quoted from the file):

Activity 1 — identify the parts: Open any .lock.yml file in your repo and find the on: key. That is the compiled trigger that came from your frontmatter.

# Example: open .github/workflows/my-workflow.lock.yml
# Find the "on:" key — that is your compiled trigger.

Learning Science Rationale:
Mayer's active-processing principle expects generative activities to require an artifact or checkable output, not just a reveal-the-answer <details> toggle; the rubric's activity_density metric (code blocks + checklist items per 100 words) reflects this by only counting verifiable artifacts. Converting one or two of the three "Activities" into short checklist items with concrete, checkable sub-steps (e.g., "- [ ] I found the on: key and wrote down its value") would both raise the measured activity density and give learners a genuine retrieval-practice moment consistent with generative-learning theory.

Improvement Prompt (for an agent):

Edit workshop/05-agentic-workflows-intro.md to raise activity_density above 3.0 and trim
word count toward 800. First, convert "Activity 1 — identify the parts" and "Activity 3 —
write a task brief" into short checklist-style sub-steps (2-3 "- [ ] ..." items each)
instead of prose-only instructions, so the rubric's checklist_items count increases.
Second, trim the "Three key terms" table's descriptive prose and the "Why This Matters"
paragraph by combining redundant sentences (target removing ~250-300 words total) without
losing the trigger/task-brief/safe-outputs definitions. Keep the existing two code blocks
and the final :white_check_mark: Checkpoint section unchanged. Run
npx --yes markdownlint-cli2 "**/*.md" after editing and confirm the file still reads
coherently end-to-end.

Expected Score After Fix: 6.7 / 10.0

Generated by 🔬 Curriculum Quality Evaluator · copilot · auto · 96.3 AIC · ⌖ 12.2 AIC · ⊞ 9.5K ·

  • expires on Sep 18, 2026, 1:02 PM UTC

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions