[workshop-sim] Repair: Add before/after example and recall check to the agentic workflows intro

[github-actions]

Problem statement

05-agentic-workflows-intro.md has the lowest active_learning score in the entire corpus (2.4/10) and checkpoint_quality 0.0/10, giving it overall_score 5.43/10. It is also the second-highest dropout step in the latest simulation: 18.7% conditional dropout among 37,157 at-risk runs (95% CI 18.3%–19.1%), with aggregate.failureCategoriesByStep attributing 4,692 failures to agentic-concept-gap — learners not internalizing the shift from deterministic Actions jobs to goal-oriented agentic workflows. The page currently explains this shift only through a comparison table (prose + table), with no worked example and no way to self-check understanding before moving on.

Proposed change

Add one short before/after example directly under the "Why This Matters for Agentic Workflows" comparison table: show a snippet of a classic deterministic step next to the equivalent agentic task-brief phrasing, then add a two-item recall-check checklist item asking the learner to state, in their own words, what changed. This is additive — it does not remove the existing comparison table or shorten any existing explanation.

Failure mode classification

Learning barrier — the gap is conceptual (no worked example, no recall check), not an access, tooling, or auth barrier; the page requires no credentials and is browser-friendly.

Quantitative guardrail

Current scores for 05-agentic-workflows-intro.md:

• overall_score: 5.43/10
• Weakest rubric dimensions: active_learning 2.4/10 (lowest in the corpus), checkpoint_quality 0.0/10
• Learning KPI index components: active_learning 2.4, checkpoint_quality 0.0, scaffolding 5.0 → index = (2.0×2.4 + 2.0×0.0 + 1.5×5.0) / 5.5 = 2.24/10

A concrete before/after example plus a recall-check item targets active_learning directly (the weakest dimension by a wide margin) and can raise checkpoint_quality if phrased as a checklist item under the rubric's recognized checkpoint pattern. Because the change adds rather than removes content, cognitive_load and readability should not degrade, so overall_score should stay flat or improve.

Acceptance criteria

• The shared curriculum quantitative assessment overall_score for 05-agentic-workflows-intro.md stays flat or improves after the change
• The step's learning KPI index (2.0 × active_learning + 2.0 × checkpoint_quality + 1.5 × scaffolding) / 5.5 stays flat or improves versus the current 2.24/10 baseline
• Hands-on practice, checkpoints, and scaffolding are preserved or strengthened — the existing comparison table and checklist remain intact, and the new example/recall-check is additive
• The new before/after example uses a concrete, runnable-looking snippet (not another abstract table) to genuinely differentiate it from existing content

Suggested owner profile

copilot coding agent (well-scoped content addition with clear acceptance criteria, suitable for automated drafting and review)
Related to #3607

Generated by 🔬 Workshop Student Simulator · copilot · auto · 248.6 AIC · ⌖ 25.8 AIC · ⊞ 14.8K · ◷

• expires on Sep 21, 2026, 1:04 PM UTC

[github-actions]

This issue is being closed as outdated. A newer issue has been created: #3616

View newer issue

---

This action was performed automatically by the Workshop Student Simulator workflow.