[workshop-sim] Improve: Add worked safe-outputs artifact activity to Step 5
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 75/100
- Issue type
- Documentation
- Clarity
- Clearly specified
- Activity status
- Active
- Tech stack
- github, javascript, yaml
- Domain
- documentation
Research direction
Start by reading 05-agentic-workflows-intro.md and locate “Activity 2 — agentic or standard?” and Activity 3. Add a short exercise between them that directs learners to a sample .lock.yml and asks them to find the safe-outputs guardrail. Done when the quantitative scores stay flat or improve and the existing activities and final checklist remain intact.
Written by the indexing model from the issue text.
Description
Problem statement
05-agentic-workflows-intro.md has the second-highest conditional dropout (19.6%, 7,717 of 39,460 at-risk runs), dominated by agentic-concept-gap (5,472 failures) and deployment-capability-gap (2,245 failures). The page's active_learning rubric score is only 2.4/10 — the lowest of any top-5 dropout step — even though it already contains three "Activity" blocks and a two-file (.md/.lock.yml) prediction exercise. The activities are mostly reveal/predict exercises without a worked example that ties the abstract "agentic vs. standard" distinction to a concrete artifact the learner can inspect in their own repository.
Proposed change
Add one additional hands-on micro-activity immediately after "Activity 2 — agentic or standard?": have the learner open a real .lock.yml file from a sample agentic workflow (link to an example in githubnext/gh-aw-workshop or a generated sample) and find the specific YAML block that encodes the task brief's safe-outputs guardrail, connecting the abstract safe-outputs term to a concrete repository artifact before Activity 3's task-brief-writing exercise. This increases hands-on activity density (activity_density) without adding conceptual density (no new terms), which should raise active_learning directly.
Failure mode classification
Learning barrier (conceptual density / insufficient scaffolding connecting abstract terms to concrete artifacts — not an access or tooling issue).
Quantitative guardrail
Current scores for 05-agentic-workflows-intro.md:
overall_score: 5.43/10- Weakest rubric dimensions:
checkpoint_quality(0.0/10) andactive_learning(2.4/10) - Learning KPI index: 2.24/10 (
active_learning2.4,checkpoint_quality0.0,scaffolding5.0)
The proposed change adds one concrete, code-block-based activity (raising activity_density and thus active_learning) without adding new vocabulary (so cognitive_load's new_concepts penalty does not worsen) and without removing the existing checklist or prerequisite section (checkpoint_quality and scaffolding unaffected). overall_score and the learning KPI index should therefore improve, not just completion.
Acceptance criteria
- The shared curriculum quantitative assessment
overall_scorefor05-agentic-workflows-intro.mdstays 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 - Hands-on practice, checkpoints, and scaffolding are preserved or strengthened — the three existing activities and the final checklist remain intact
- The new activity links an abstract term (safe outputs) to a concrete, inspectable
.lock.ymlartifact and does not introduce new unexplained vocabulary
Suggested owner
copilot coding agent
Related to #4493
Generated by 🔬 Workshop Student Simulator · copilot · auto · 309.7 AIC · ⌖ 14.8 AIC · ⊞ 15.1K · ◷
- expires on Oct 13, 2026, 8:28 AM UTC
- Dominant language
- JavaScript
- Stars
- 53
- Forks
- 35
- Avg merge
- 13h 50m
- Merged PRs (30d)
- 14
Getting set up
Starts the project's dev container in your browser, under your own GitHub account.
- No Dockerfile or Docker Compose file
- No pull request template
- No contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from githubnext/gh-aw-workshop
-
[curriculum-eval] 04-github-actions-intro.md: cognitive_load — 28 new concepts in a 5-minute introOpencurriculum documentation quality
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
githubnext/gh-aw-workshop#4603 ·
Maintainers usually reply within 1 day
-
curriculum documentation quality
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
githubnext/gh-aw-workshop#4601 ·
Maintainers usually reply within 1 day
-
curriculum documentation quality
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
githubnext/gh-aw-workshop#4578 ·
Maintainers usually reply within 1 day
-
documentation
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
githubnext/gh-aw-workshop#4577 ·
Maintainers usually reply within 1 day
-
[guidelines] side-quest-21-01-sub-agent-syntax.md: checklist checkbox count exceeds 10-item limitOpendocumentation guidelines
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
githubnext/gh-aw-workshop#4409 ·
Maintainers usually reply within 1 day
All issues in githubnext/gh-aw-workshop
Similar issues
-
[BUG]: Prompt compressor crashes with TypeError when a past chat has a non-string response.textPossibly taken @ManojDevarajulu claimed this today. Openpossible bug
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
Mintplex-Labs/anything-llm#6737 ·
Maintainers usually reply within 1 day
-
check:passed feeds:add
Difficulty 2/5 Under an hour Newbie friendliness 62/100
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
codex-team/editor.js#3037 ·
-
No Code Attached Yet
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
joomla/joomla-cms#48626 ·
Maintainers usually reply within 1 day
-
complexity: trivial good first issue impact: low
Difficulty 1/5 Under an hour Newbie friendliness 78/100
ueberdosis/tiptap#8522 ·
Maintainers usually reply within 1 day