[workshop-sim] Improve: Add before/after summary and GHES signpost to Step 5 (What Are Agentic Workflows?)

[github-actions]

Problem statement

05-agentic-workflows-intro.md (Step 5) is the second-highest-dropout step: 18.0% conditional dropout among 36,222 at-risk simulated runs (95% CI 17.6%–18.4%), split between an agentic-concept-gap failure mode (~4,396 failures — learners don't fully internalize the shift from deterministic jobs to goal-oriented agentic workflows) and a smaller deployment-capability-gap (~2,137 failures — GHES learners hit an enablement gap the content treats only conditionally).

Proposed change

1. Add a compact "before/after" summary table (2–3 rows) directly under the "Three key terms" table that puts a classic Actions step and its agentic equivalent side by side, reinforcing the shift in one glance for learners who skim the diagram.
2. For the GHES branch, add a short explicit callout (near "Before You Start") pointing GHES learners at the existing GHES enablement check before they proceed to Activity 1, rather than leaving it implicit in deployment context alone.
   Keep all three existing activities (parts, predict, agentic-or-standard, task-brief) intact — this adds a summary and a GHES signpost, it does not replace practice.

Failure mode classification

Learning barrier (concept gap, majority of failures) with a secondary access barrier (GHES enablement, minority of failures).

Quantitative guardrail

• Current overall_score: 5.43/10
• Weakest rubric dimension: active_learning (2.4/10) and checkpoint_quality (0.0/10, corpus-wide detection gap — not targeted by this repair)
• Current learning KPI index: active_learning 2.4, checkpoint_quality 0.0, scaffolding 5.0 → index = 2.24/10
• The added before/after table and GHES callout increase active_learning (an additional worked comparison) and scaffolding (an explicit prerequisite branch for GHES learners) without adding cognitive load beyond a compact table, so overall_score and the learning KPI index should rise, not fall.

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
• Activities 1–3 (predict, agentic-or-standard, task-brief) and the full checkpoint checklist remain unchanged and are not shortened or removed
• npx --yes markdownlint-cli2 "**/*.md" passes with no new violations

Suggested owner

workshop maintainer
Related to #3139

Generated by 🔬 Workshop Student Simulator · copilot · auto · 231.3 AIC · ⌖ 7.23 AIC · ⊞ 15.2K · ◷

• expires on Sep 10, 2026, 10:50 PM UTC

[github-actions]

This issue is being closed as outdated. A newer issue has been created: #3148

View newer issue

---

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