[workshop-sim] Improve: Add per-activity checkpoints to agentic workflows intro (05-agentic-workflows-intro.md)
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 64/100
- Issue type
- Documentation
- Clarity
- Clearly specified
- Activity status
- Active
- Tech stack
- markdown
- Domain
- documentation
Research direction
Start in 05-agentic-workflows-intro.md and locate the three activity headings and their reveal-answer <details> blocks. Add a short 1-2 item checkpoint right after each block, leaving the existing activities, the two-file-structure diagram, and the glossary link unchanged, then check the new text against the end-of-page checklist. Done when each activity has its own checkpoint and npx --yes markdownlint-cli2 "**/*.md" reports no new errors.
Written by the indexing model from the issue text.
Description
Problem statement
05-agentic-workflows-intro.md has the single highest total failure count in the simulated cohort (7,350 failures across 1,000×46 runs) and the second-highest conditional dropout rate (19.9% among 36,952 at-risk runs), driven by agentic-concept-gap (5,204 failures) and deployment-capability-gap (2,146 failures). The step scores the lowest active_learning (2.4/10) in the entire curriculum despite stacking three distinct activities back-to-back — opening a .lock.yml to find on:, classifying Task A/B as agentic-or-standard, and writing/self-grading a task brief — with only one optional "Still uncertain?" disclosure as mid-page recovery support and no activity-level checkpoint beyond the final checklist.
Proposed change
Give each of the three activities ("Activity 1 — identify the parts", "Activity 2 — agentic or standard?", "Activity 3 — write a task brief") its own short inline checkpoint (a 1-2 item checklist or explicit "did you get this right?" prompt) immediately after its reveal-answer <details> block, instead of deferring all verification to the single end-of-page checklist. Keep all three activities, the two-file-structure diagram, and the glossary side-quest link exactly as they are — the content is appropriately dense for this concept, it just lacks incremental verification.
Failure mode classification: Learning barrier (conceptual density combined with weak intermediate checkpoints, not an access or tooling issue).
Quantitative guardrail
- Current
overall_score: 5.43/10 - Weakest rubric dimensions:
active_learning2.4/10 (lowest in the entire 30-step corpus),checkpoint_quality0.0/10 (shared detection gap across all 30 steps — see report) - Current learning KPI index for this step:
(2.0×2.4 + 2.0×0.0 + 1.5×5.0) / 5.5= 2.24/10 (active_learning 2.4, checkpoint_quality 0.0, scaffolding 5.0) - Adding per-activity checkpoints directly targets
active_learningandcheckpoint_qualitywithout changing word count materially or removing any existing activity, sooverall_scoreand the learning KPI index should rise, not fall.
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)/5.5stays flat or improves - All three existing hands-on activities (Activity 1, 2, 3) and their reveal-answer
<details>blocks are preserved, with new checkpoints added rather than content removed - Markdown passes
npx --yes markdownlint-cli2 "**/*.md"with no new errors
Suggested owner: workshop maintainer
Related to #4367
Generated by 🔬 Workshop Student Simulator · copilot · auto · 163.7 AIC · ⌖ 12.2 AIC · ⊞ 15.1K · ◷
- expires on Oct 10, 2026, 7:10 AM UTC
- Dominant language
- JavaScript
- Stars
- 52
- Forks
- 26
- Avg merge
- 12h 25m
- Merged PRs (30d)
- 18
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
-
feedback simulation workshop
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
githubnext/gh-aw-workshop#4370 ·
Maintainers usually reply within 1 day
-
feedback simulation workshop
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
githubnext/gh-aw-workshop#4368 ·
Maintainers usually reply within 1 day
-
documentation
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
githubnext/gh-aw-workshop#4366 ·
Maintainers usually reply within 1 day
-
documentation
Difficulty 1/5 Under an hour Newbie friendliness 88/100
githubnext/gh-aw-workshop#4365 ·
Maintainers usually reply within 1 day
-
documentation guidelines
Difficulty 1/5 Under an hour Newbie friendliness 88/100
githubnext/gh-aw-workshop#4363 ·
Maintainers usually reply within 1 day
All issues in githubnext/gh-aw-workshop
Similar issues
-
[BUG] Multi-day events show "Ended" while still in progressPossibly taken @tarunagnihotri534 claimed this today. Openbug
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
data-umbrella/du-event-board#231 · 2 comments ·
-
Difficulty 1/5 Under an hour Newbie friendliness 78/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
NaturalIntelligence/fast-xml-parser#888 · 1 comment ·
Maintainers usually reply within 2 days
-
Difficulty 1/5 Under an hour Newbie friendliness 80/100
USACE/chart-docs#766 ·
-
bug callouts regression revealjs
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
quarto-dev/quarto-cli#15014 ·
Maintainers usually reply within 1 day