[curriculum-eval] 05-agentic-workflows-intro.md: cognitive_load — diagram-duplicating prose pushes word count 307 words over budget

**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 | 10 (≤800 words, ≤15 concepts) | -1.5 (1107 words vs 800 ideal; 15 concepts is at the limit) |
| active_learning | 2.4 | ≥3 activity density | -0.6 (density 0.72 vs 3.0 ideal) |
| checkpoint_quality | 0.0 | 10 (≥4 checklist items) | -10.0 (scorer defect — see Root Cause) |

**Root Cause (≤ 2 sentences):**
This page already contains three good active-learning exercises (Activity 1, 2, 3) and two diagrams, but at 1107 words it runs 307 words over the cognitive-load budget, and its activity density (0.72) is still low relative to word count because each of the three activities is followed by lengthy explanatory prose rather than being tightly self-contained. `checkpoint_quality` also reads 0.0 due to the corpus-wide `## :white_check_mark: Checkpoint` vs. `## ✅ Checkpoint` scorer mismatch — the actual checkpoint has 6 solid items plus a bonus reflection block and is not the real gap.

**Evidence (quoted from the file):**
> An **Agentic Workflow** is a plain-English task brief that an AI agent executes inside GitHub Actions. You write what you want — "summarize open issues and post a daily digest" — and the agent reads your repo, calls tools, and posts the output automatically.
>
> Think of it like a scheduled digest: every morning it reads your inbox and sends you a summary — no keyboard required.

**Learning Science Rationale:**
Mayer's Multimedia Principles include the "redundancy principle" — supplementing a diagram with excessive parallel prose narration (here, the "two-file structure" diagram is followed by a full paragraph re-explaining what the diagram already shows, plus a separate `.md`/`.lock.yml` bullet recap) can increase extraneous cognitive load rather than reduce it, because learners must reconcile two representations of the same information instead of processing one efficiently.

**Improvement Prompt (for an agent):**
```
Open workshop/05-agentic-workflows-intro.md. Trim the prose that duplicates information already shown in the two diagrams (the "three key terms" diagram and the "two-file structure"/lifecycle diagram) — specifically shorten the paragraph before "Three key terms" and the bullet recap under "The two-file structure" so they add new framing rather than restating the diagram captions. Target an overall word count reduction from 1107 to roughly 850-900 words while keeping all three existing activities (Activity 1, 2, 3) and the checkpoint intact. Run `npx --yes markdownlint-cli2 "**/*.md"` after editing and fix any lint errors.
```

**Expected Score After Fix:** `6.5 / 10.0`

> Generated by [🔬 Curriculum Quality Evaluator](https://github.com/githubnext/gh-aw-workshop/actions/runs/35026063971) · copilot · auto · 76.1 AIC · ⌖ 8.13 AIC · ⊞ 9.5K · [◷](https://github.com/search?q=repo%3Agithubnext%2Fgh-aw-workshop+is%3Aissue+%22gh-aw-workflow-call-id%3A+githubnext%2Fgh-aw-workshop%2Fcurriculum-evaluator%22&type=issues)
> - [x] expires on Sep 16, 2026, 9:39 PM UTC

Open workshop/05-agentic-workflows-intro.md and compare the prose before “Three key terms” and the bullet recap under “The two-file structure” with the two diagrams. Shorten duplicated explanations while preserving Activities 1, 2, 3 and the checkpoint, targeting roughly 850–900 words. Run npx --yes markdownlint-cli2 "**/*.md" and fix any lint errors.

Written by the indexing model from the issue text.